ISCA - International Speech
Communication Association

ISCApad Archive  »  2021  »  ISCApad #277  »  Events

ISCApad #277

Saturday, July 10, 2021 by Chris Wellekens

3 Events
3-1 ISCA Events
3-1-1(2021-08-30) Interspeech 2021 Agenda (updated)

 June 10, 2021 (midnight CET)    Travel grant application deadline

  • June 18, 2021    Travel grant notifications sent


Dear Interspeech participants, dear speech community,

We have reached an importnant milestone: our technical chairs are sending the paper acceptance/rejection notifications today. We received 1985 submissions that we sent out for review, of which 966 were selected for presentation at the conference - thank a lot to everyone that submitted high quality papers!

The Technical Chairs experienced problem with emails to some countries and institutions - in case you await decision of your paper and have not received it, please check the status of your paper in the START system and check instructions for authors of accepted papers

The travel restrictions, at least in Central Europe, are gradually being relaxed, and we have the hope that we will be able to organize Interspeech 2021 in a hybrid format. At the same time, we are aware that many colleagues won´t be able to make it to Brno due to Government regulations, employer restrictions on business travel, or because of family or health issues. Therefore, we are preparing the conference in order to ensure that remote participants have the best possible experience. As was originally announced, the decision 'hybrid vs. fully virtual' will be taken by June 20 based on covering author registrations.

Please mind the following dates:

  • June 15 - Submission of revised papers and registration of author(s) covering the accepted papers. This is a firm deadline and no extension will be granted for any reason.

  • June 10(midnight CET) Travel grant application deadline

  • June 18, Travel grant notifications sent

  • June 20 - Final decision on the format of Interspeech 2021 - hybrid or fully virtual

  • June 25 - Registration of paper presenters

  • June 30 - Paper presentation instructions

  • July 15 - Schedule of papers will be available and instructions for presentation will be published on the Interspeech 2021 website and by email to authors and presenters.

  • August 10 - Submission of videos, eventually other material for Unified virtual sessions. Deadline of Request for Virtual gatherings.

  • August 30 - September 3 - Interspeech 2021

We are sorry for any inconvenience and uncertainty, please stay with us while we´re trying hard to make Interspeech 2021 (in any format) a success. We hope to see you in Brno in August/September!

Hynek Hermanský - General Chair

Honza Cernocký - General Chair


Due to the changes we need to implement, the registration system is temporarily disabled and will reopen on June 8th.



3-1-2(2021-08-30) Interspeech 2021 Brno goes hybrid!

Dear Interspeech participants, dear speech community, 

We are announcing that Interspeech 2021 will take place in HYBRID FORM - the conference will happen both physically in Brno and virtually, giving the opportunity to connect to all of you that won?t be able to make it to Brno. 

May we ask 

  • those of you who have not yet registered, please do not forget the early registration deadline on June 25th. 

  • those of you who change your registration based on this information from virtual to physical, to do so as early as possible, especially in case you are a paper presenter - the session building needs to take this into account. Do this by emailing the conference secretariat at

Let us remind you however that the COVID-19 crisis is not over, and that:

  • It is your responsibility to check that you are allowed to travel to Brno - this includes your country regulations, Czech regulations and your employer rules for business travel and/or reimbursement of costs. 

  • In Brno, we will have to respect the Czech Government COVID regulations, see for example for the current status. While the measures are being gradually relaxed, we need to count on checking COVID-19 tests or vaccinations at the conference, and we might need to wear face-masks when inside. These conditions are dynamically evolving and, as the organizers, we are not in a position to change them. 

Details and instructions for both physical and remote paper presentations will follow soon.

We are looking forward to seeing you in Brno or virtually in August/September!

Hynek He?manský - General Chair  
Honza ?ernocký - General Chair


3-1-3(2021-08-30) Interspeech 2021, Brno, Czechia

ISCA and General chairs message for web and ISCAPad - end January 2021



Dear Interspeech participants, dear speech community, 


While we recognize the challenges for our Shanghai colleagues that had to turn Interspeech 2020 to virtual mode, we were hoping that 2021 would bring improvement on the COVID front and that we would see the speech community physically in Brno, our beloved city. Unfortunately, the situation at the beginning of 2021 is not that positive, with high numbers of new cases, strict Government regulations, lock-downs and actually stopped cross-border travel. We hope the situation will improve as we approach summer, but with the current (slow) progress with vaccination, and travel bans some big companies and Universities have issued, we would be naive to think that our Interspeech will be a “normal” one. 


We have therefore decided to opt for a hybrid Brno Interspeech with a back-up option of fully virtual one


How will it look like ? 

  1. The paper submission and review will proceed as usual, with the deadline of March 26. Despite the restriction, we encourage our community to submit quality papers !


  1. At registration, we will ask participants to select physical or virtual presence at the conference. Both physical and virtual participants will have the same access to the talks and posters at the conference. Of course, we can’t provide the excellent Czech beer to virtual participants... The registration fees for virtual participants will be half of the physical ones, with no penalty for switching from virtual to physical (with surcharge to full physical fee) and very little extra when switching from physical to virtual. More details about conditions will be available on the registration website.


  1. We have cancelled the large BVV conference center and booked a conference Hotel Internationalright in the historical center of Brno. The tutorials will take place (also in hybrid mode) at the Faculty of Information Technology of BUT. Out of the usual 12 parallel sessions. Part will run in hybrid (virtually and physically) and part in only virtual mode. We will do our best that they have the same level of interaction. The selection of papers into hybrid sessions will be based on who comes physically to Brno, we will try to respect the usual topicality of sessions, but might have a bit more overlap than usually. 


  1. As we move forward with Interspeech-2021 logistics, we will continue to stay connected with those organizing ISCA satellite workshops and special events. We look forward to a technically inspiring Interspeech program with complementary workshops. 


  1. The author registration deadline June 15 will be important - in the unfortunate case of having too few participants able/willing to come to Brno, we will have to “pull the emergency brake” and switch Interspeech 2021 to fully virtual. Therefore, we kindly ask everyone to wait with purchase of air-tickets until the decision is done (around June 20). At the same time, we are closely watching  related international events as well as similarly sized events in Czechia to be able to do the most informed decision. 


We are sorry for any inconvenience and uncertainty, please stay with us while we’re trying hard to make Insterspeech 2021 (in any format) a success.  We hope to see you in Brno in August/September !


Hynek Heřmanský - General Chair  

Honza Černocký - General Chair

John H.L. Hansen - ISCA President 

Sebastian Möller - ISCA Conferences 

Margaret Zellers - ISCA Conferences


3-1-4(2022-09-18) Interspeech 2022, Incheon, South Korea

Incheon in South Korea will welcome Interspeech 2022.


3-1-5(2023-08-20) Interspeech 2023, Dublin, Ireland

, ISCA has reached the decision to hold INTERSPEECH-2023 in Dublin, Ireland (Aug. 20-24, 2023)


3-1-6(2024-09-01) Interspeech 2024, Jerusalem, Israel.

 ISCA conference committee has decided Interspeech 2024 will be held in Jerusalem, Israel from

September 1 till September 5.




Now's the time of year that seminar programmes get fixed up.. please direct the attention of whoever organises your seminars to the ISCA INTERNATIONAL VIRTUAL SEMINARS scheme (introduction below). There is now a good choice of speakers:  see


A seminar programme is an important part of the life of a research lab, especially for its research students, but it's difficult for scientists to travel to give talks at the moment. However,  presentations may be given on line and, paradoxically, it is thus possible for labs to engage international speakers who they wouldn't normally be able to afford.

ISCA has set up a pool of speakers prepared to give on-line talks. In this way we can enhance the experience of students working in our field, often in difficult conditions. To find details of the speakers,

  • visit
  • Click Distinguished Lecturers in the left panel
  • Online Seminars then appears beneath Distinguished Lecturers: click that.

Speakers may pre-record their talks if they wish, but they don't have to. It is up to the host lab to contact speakers and make the arrangements. Talks can be state-of-the-art, or tutorials.

If you make use of this scheme and arrange a seminar, please send brief details (lab, speaker, date) to

If you wish to join the scheme as a speaker, we need is a title, a short abstract, a 1 paragraph biopic and contact details. Please send them to

PS. The online seminar scheme  is now up and running, with 7 speakers so far:


Jean-Luc Schwartz, Roger Moore, Martin Cooke, Sakriani Sakti, Thomas Hueber, John Hansen and Karen Livescu.


3-1-8Speech Prosody courses

Dear Speech Prosody SIG Members,

We would like to draw your attention to three upcoming short courses from the Luso-Brazilian Association of Speech Sciences:

- Prosody & Rhythm: applications to teaching rhythm,
  Donna Erickson (Haskins), March 16, 19, 23 and 26

- Prosody, variation and contact,
  Barbara Gili Fivela (University of Salento, Italy), April 19, 21, 23, 26 and 28

- Rhythmic analysis of languages: main challenges,
  Marisa Cruz (University of Lisbon), June 2, 3, 4, 7, 8 and 10

For details:
Plinio Barbosa and Nigel Ward


3-2 ISCA Supported Events
3-2-1(2022-05-23) Speech Prosody 2022, Lisbon, Portugal

 The Speech Prosody 2022 website is now live, at ,?
with the Call for Papers and information on the venue, etc. 

Dear SProSIG Members,

I am pleased to announce that Speech Prosody 2022 will be held in Lisbon,  May 23-26, 2022.

Thanks to all who voted: 315 members from 46 countries.  Although the vote for Lisbon was decisive (41%), it was good to see strong support also for the bids for Aix (33%) and Nijmegen (26%).
Nigel Ward, SProSIG Chair
Professor of Computer Science, University of Texas at El Paso


3-2-2The International Conference 'Language Technologies for All (LT4All): a report.

The International Conference 'Language Technologies for All (LT4All):  
Enabling Linguistic Diversity and Multilingualism Worldwide', which took  
place on December 4-6, 2019 at Unesco Headquarters in Paris in the  
framework of the International Year of Indigenous Languages (IYIL 2019),  
was sponsored by ISCA. 
The rationale of the conference was: 'How to improve the present  
situation where only 2% of the languages spoken over the world benefit  
from Language Technologies' ? 
 Out of the 7,000+ language spoken around the world, only a few have associated Language
Technologies. The majority of languages can be considered as 'under-resourced' or as 'not
supported'. This situation, very detrimental to many languages speakers, and specifically
indigenous languages speakers, creates a digital divide,  and places many languages in
danger of digital extinction, if not complete extinction.

Organized as part of the 2019 International Year of Indigenous Languages, the 1st edition
of LT4All (Language Technologies for All: Enabling Linguistic Diversity and
Multilingualism Worldwide) took place in Paris at the UNESCO Headquarters on December
4-6, 2019 and gathered 400 participants from various backgrounds (including language
science and technology researchers, linguists, industrials, indigenous peoples, language
policy and decision makers) from all over the world.

 It allowed for fruitful exchanges between Language Technology providers  
and Language Policy makers, as it can be seen on Twitter: 
The conference oral sessions were webcasted and can be replayed, in  
English and French: see 

The LT4All Programme and Editorial Committees are very happy to announce that the set of
Research Papers and Posters collected at the occasion of LT4All is now available online
at :

LT4All has  been made possible thanks to the close cooperation between UNESCO, the 
Government of the Khanty-Mansiysk Autonomous Okrug-Ugra (Russian Federation), the
European Language Resources Association (ELRA) and its Special Interest  Group on
Under-resourced  languages  (SIGUL), and in partnership with UNESCO Intergovernmental
Information for All Programme (IFAP) and the Interregional Library Cooperation Centre, as
well as with support of other public organizations, including ISCA, and sponsors.

More information including the list of all the sponsors and supporters @


3-3 Other Events
3-3-1(2021-07-12) ACM International Conference on Multimedia Retrieval 2021, Taipei,Taiwan

ACM International Conference on Multimedia Retrieval 2021

Taipei, Taiwan, July 12--15, 2021


ACM ICMR 2021 is calling for high quality original papers addressing innovative research in multimedia retrieval and its related broad fields. The main scope of the conference is not only search and retrieval of multimedia data but also analysis and understanding of multimedia contents including community-contributed social data, lifelogging data and automatically generated sensor data, integration of diverse multimodal data, deep learning-based methodology and practical multimedia applications.


We are seeking original high quality submissions addressing innovative research in the field. Contributions addressing the challenges of large-scale search and user behavior analysis are especially welcome.


Topics of interest include (but are not limited to):

?- Multimedia content-based search and retrieval;

?- Multimedia-content-based (or hybrid) recommender systems;

?- Large-scale and web-scale multimedia retrieval;

?- Multimedia content extraction, analysis, and indexing;

?- Multimedia analytics and knowledge discovery;

?- Multimedia machine learning, deep learning, and neural nets;

?- Relevance feedback, active learning, and transfer learning;

?- Zero-shot learning and fine-grained retrieval for multimedia;

?- Event-based indexing and multimedia understanding;

?- Semantic descriptors and novel high- or mid-level features;

?- Crowdsourcing, community contributions, and social multimedia;

?- Multimedia retrieval leveraging quality, production cues, style, framing, affect;

?- Narrative generation and narrative analysis;

?- User intent and human perception in multimedia retrieval;

?- Query processing and relevance feedback;

?- Multimedia browsing, summarization, and visualization;

?- Multimedia beyond video, including 3D data and sensor data;

?- Mobile multimedia browsing and search;

?- Multimedia analysis/search acceleration, e.g., GPU, FPGA;

?- Benchmarks and evaluation methodologies for multimedia analysis/search;

?- Applications of multimedia retrieval, e.g., medicine, sports, commerce, lifelogs, travel, security, environment.


Important Dates

Deadline for Full/Short/Special Session/Brave New Idea Paper Submission: February 21, 2021

Deadline for Demo/Doctoral Symposium Paper Submission: March 21, 2021

Acceptance Notification of Full/Short/Special Session/Demo/Doctoral Symposium Papers: April 11, 2021

Deadline for Workshop Paper Submission: April 20, 2021

Acceptance Notification of Workshop Papers: May 20, 2021


3-3-2(2021-07-26) 4th INTERNATIONAL SCHOOL ON DEEP LEARNING, Las Palmas de Gran Canaria, Spain


DeepLearn 2021 Summer
Las Palmas de Gran Canaria, Spain
July 26-30, 2021
Co-organized by:
Department of Information Engineering
Marche Polytechnic University
Institute for Research Development, Training and Advice ? IRDTA
--- Early registration deadline: January 25, 2021 ---
DeepLearn 2021 Summer will be a research training event with a global scope aiming at updating participants on the most recent advances in the critical and fast developing area of deep learning. Previous events were held in Bilbao, Genova and Warsaw.
Deep learning is a branch of artificial intelligence covering a spectrum of current exciting research and industrial innovation that provides more efficient algorithms to deal with large-scale data in neurosciences, computer vision, speech recognition, language processing, human-computer interaction, drug discovery, biomedical informatics, healthcare, recommender systems, learning theory, robotics, games, etc. Renowned academics and industry pioneers will lecture and share their views with the audience.
Most deep learning subareas will be displayed, and main challenges identified through 24 four-hour and a half courses and 3 keynote lectures, which will tackle the most active and promising topics. The organizers are convinced that outstanding speakers will attract the brightest and most motivated students. Interaction will be a main component of the event.
An open session will give participants the opportunity to present their own work in progress in 5 minutes. Moreover, there will be two special sessions with industrial and recruitment profiles.
Master's students, PhD students, postdocs, and industry practitioners will be typical profiles of participants. However, there are no formal pre-requisites for attendance in terms of academic degrees. Since there will be a variety of levels, specific knowledge background may be assumed for some of the courses. Overall, DeepLearn 2021 Summer is addressed to students, researchers and practitioners who want to keep themselves updated about recent developments and future trends. All will surely find it fruitful to listen and discuss with major researchers, industry leaders and innovators.
DeepLearn 2021 Summer will take place in Las Palmas de Gran Canaria, on the Atlantic Ocean, with a mild climate throughout the year, sandy beaches and a renowned carnival. The venue will be:
Palacio de Congresos Gran Canaria
Institución Ferial de Canarias
Avenida de la Feria, 1
35012 Las Palmas de Gran Canaria
3 courses will run in parallel during the whole event. Participants will be able to freely choose the courses they wish to attend as well as to move from one to another.
Nello Cristianini (University of Bristol), Data, Intelligence and Shortcuts
Petia Radeva (University of Barcelona), Uncertainty Modeling and Deep Learning in Food Analysis
Indr? ?liobait? (University of Helsinki), Any Hope for Deep Learning in Deep Time?
PROFESSORS AND COURSES: (to be completed)
Ignacio Arganda-Carreras (University of the Basque Country), [introductory/intermediate] Deep Learning for Bioimage Analysis
Thomas G. Dietterich (Oregon State University), [introductory] Machine Learning Methods for Robust Artificial Intelligence
Georgios Giannakis (University of Minnesota), [advanced] Ensembles for Online, Interactive and Deep Learning Machines with Scalability, and Adaptivity
Sergei V. Gleyzer (University of Alabama), [introductory/intermediate] Machine Learning Fundamentals and Their Applications to Very Large Scientific Data: Rare Signal and Feature Extraction, End-to-end Deep Learning, Uncertainty Estimation and Realtime Machine Learning Applications in Software and Hardware
Ça?lar Gülçehre (DeepMind), [intermediate/advanced] Deep Reinforcement Learning
Balázs Kégl (Huawei Technologies), [introductory] Deep Model-based Reinforcement Learning
Vincent Lepetit (ENPC ParisTech), [intermediate] Deep Learning and 3D Geometry
Geert Leus (Delft University of Technology), [introductory/intermediate] Graph Signal Processing: Introduction and Connections to Distributed Optimization and Deep Learning
Andy Liaw (Merck Research Labs), [introductory] Machine Learning and Statistics: Better together
Abdelrahman Mohamed (Facebook AI Research), [introductory/advanced] Recent Advances in Automatic Speech Recognition
Hermann Ney (RWTH Aachen University), [intermediate/advanced] Speech Recognition and Machine Translation: From Statistical Decision Theory to Machine Learning and Deep Neural Networks
Lyle John Palmer (University of Adelaide), [introductory/advanced] Epidemiology for Machine Learning Investigators
Jan Peters (Technical University of Darmstadt), [intermediate] Robot Learning
José C. Príncipe (University of Florida), [intermediate/advanced] Cognitive Architectures for Object Recognition in Video
Björn W. Schuller (Imperial College London), [introductory/intermediate] Deep Signal Processing
Sargur N. Srihari (University at Buffalo), [introductory] Generative Models in Deep Learning
Johan Suykens (KU Leuven), [introductory/intermediate] Deep Learning, Neural Networks and Kernel Machines
Gaël Varoquaux (INRIA), [intermediate] Representation Learning in Limited Data Settings
René Vidal (Johns Hopkins University), [intermediate/advanced] Mathematics of Deep Learning
Haixun Wang (Instacart), [introductory/intermediate] Abstractions, Concepts, and Machine Learning
Ming-Hsuan Yang (University of California, Merced), [intermediate/advanced] Learning to Track Objects
An open session will collect 5-minute voluntary presentations of work in progress by participants. They should submit a half-page abstract containing the title, authors, and summary of the research to by July 18, 2021.
A session will be devoted to 10-minute demonstrations of practical applications of deep learning in industry. Companies interested in contributing are welcome to submit a 1-page abstract containing the program of the demonstration and the logistics needed. People participating in the demonstration must register for the event. Expressions of interest have to be submitted to by July 18, 2021.
Firms searching for personnel well skilled in deep learning will have a space reserved for one-to-one contacts. It is recommended to produce a 1-page .pdf leaflet with a brief description of the company and the profiles looked for to be circulated among the participants prior to the event. People in charge of the search must register for the event. Expressions of interest have to be submitted to by July 18, 2021.
Emanuele Frontoni (Ancona, co-chair)
Carlos Martín-Vide (Tarragona, program chair)
Sara Moccia (Ancona)
Sara Morales (Brussels)
Marina Paolanti (Ancona)
Manuel J. Parra-Royón (Granada)
Luca Romeo (Ancona)
David Silva (London, co-chair)
It has to be done at
The selection of up to 8 courses requested in the registration template is only tentative and non-binding. For the sake of organization, it will be helpful to have an estimation of the respective demand for each course. During the event, participants will be free to attend the courses they wish.
Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration tool disabled when the capacity of the venue will get exhausted. It is highly recommended to register prior to the event.
Fees comprise access to all courses and lunches. There are several early registration deadlines. Fees depend on the registration deadline.
Suggestions for accommodation will be available in due time at
A certificate of successful participation in the event will be delivered indicating the number of hours of lectures.
Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche
Institute for Research Development, Training and Advice ? IRDTA, Brussels/London
Institución Ferial de Canarias


3-3-3(2021-07-29) SIGDIAL 2021 Conference, Singapore



July 29-31, 2021


The 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2021) will be held on July 29-31, 2021 in Singapore.


SIGDIAL will be temporally co-located with ACL-IJCNLP 2021, which will be held on August 1-6 in Bangkok, Thailand ( ).


The SIGDIAL venue provides a regular forum for the presentation of cutting edge research in discourse and dialogue to both academic and industry researchers. Continuing a series of twenty successful previous meetings, this conference spans the research interest areas of discourse and dialogue. The conference is sponsored by the SIGdial organization, which serves as the Special Interest Group in discourse and dialogue for both ACL and ISCA.




- Special Sessions


SIGDIAL 2021 will have two special sessions:


  - Safety for E2E Conversational AI

  - SummDial: Summarization of Multi-Party Dialogues and Meetings


Papers submitted for these special sessions as SIGDIAL regular papers will be reviewed in the same way as other SIGDIAL submissions. The submission deadline and the paper format are the same. Please see their websites for details (including different types of paper submissions and deadlines).


- Hybrid Conference


SIGDIAL 2021 is preparing for a hybrid in-person and virtual conference where people can participate online if they want.



We welcome formal, corpus-based, implementation, experimental, or analytical work on discourse and dialogue including, but not restricted to, the following themes:


- Discourse Processing: Rhetorical and coherence relations, discourse parsing, and discourse connectives. Reference resolution. Event representation and causality in the narrative. Argument mining. Quality and style in text. Cross-lingual discourse analysis. Discourse issues in applications such as machine translation, text summarization, essay grading, question answering, and information retrieval.


- Dialogue Systems: Open-domain, task-oriented dialogue, and chat systems. Knowledge graphs and dialogue. Dialogue state tracking and policy learning. Social and emotional intelligence. Dialogue issues in virtual reality and human-robot interaction. Entrainment, alignment, and priming. Generation for dialogue. Style, voice, and personality. Spoken, multimodal, embedded, situated, and text/web-based dialogue systems, their components, evaluation, and applications.


- Corpora, Tools and Methodology: Corpus-based and experimental work on discourse and dialogue, including supporting topics such as annotation tools and schemes, crowdsourcing, evaluation methodology, and corpora.


- Pragmatic and/or Semantic Modeling: Pragmatics or semantics of discourse and dialogue (i.e., beyond a single sentence).


- Applications of Dialogue and Discourse Processing Technology



Long, Short & Demonstration Paper Submission: April 2, 2021 (11:59pm GMT-11)

Long, Short & Demonstration Paper Notification: May 24, 2021

Final Paper Submission: June 8, 2021

Conference: July 29-31, 2021




The program committee welcomes the submission of long papers, short papers, and demo descriptions. Papers submitted as long papers may be accepted as long papers for oral presentation or long papers for a poster presentation. Accepted short papers will be presented as posters.


- Long paper submissions must describe substantial, original, completed, and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Long papers must be no longer than 8 pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices containing sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers? comments.


- Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Instead, short papers should have a point that can be made in a few pages, such as a small, focused contribution; a negative result; or an interesting application nugget. Short papers should be no longer than 4 pages including title, text, figures, and tables. An unlimited number of pages is allowed for references. One additional page is allowed for sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers? comments.


- Demo descriptions should be no longer than four pages including title, text, examples, figures, tables, and references. A separate one-page document should be provided to the program co-chairs for demo descriptions, specifying furniture and equipment needed for the demo.


Authors are encouraged to also submit additional accompanying materials, such as corpora (or corpus examples), demo code, videos, and sound files.


Multiple Submissions


SIGDIAL 2021 cannot accept work for publication or presentation that will be (or has been) published elsewhere and that has been or will be submitted to other meetings or publications whose review periods overlap with that of SIGDIAL. Any questions regarding submissions can be sent to conference[at]


Blind Review


SIGDIAL 2021 will follow the ACL policies for preserving the integrity of double-blind review (see author guidelines). Unlike long and short papers, demo descriptions will not be anonymous. Demo descriptions should include the authors? names and affiliations, and self-references are allowed.


Submission Format


All long, short, and demonstration submissions must follow the two-column ACL format. Authors are expected to use the LaTeX or Microsoft Word style template from the ACL conference.

Submissions must conform to the official ACL style guidelines, which are contained in these templates. Submissions must be electronic, in PDF format.


Authors have to fill in the submission form in the START system and upload an initial pdf of their papers before the April 2, 2021 deadline (23:59 GMT-11).  Please see the conference website for details.


For special session long and short papers please select the session under ?Submission Type?.



As noted above, SIGDIAL 2021 is adopting the ACL guidelines for submission and citation for long and short papers. Long and short papers that do not conform to the following guidelines will be rejected without review.

Preserving Double Blind Review


The following rules and guidelines are meant to protect the integrity of the double-blind reviewing process and ensure that submissions are reviewed fairly. The rules make reference to the anonymity period, which runs from 1 month before the submission deadline up to the date when your paper is either accepted, rejected, or withdrawn.


- You may not make a non-anonymized version of your paper available online to the general community (for example, via a preprint server) during the anonymity period. By a version of a paper, we understand another paper having essentially the same scientific content but possibly differing in minor details (including title and structure) or in length (e.g., an abstract is a version of the paper that it summarizes).

- If you have posted a non-anonymized version of your paper online before the start of the anonymity period, you may submit an anonymized version to the conference. The submitted version must not refer to the non-anonymized version, and you must inform the program chair(s) that a non-anonymized version exists. You may not update the non-anonymized version during the anonymity period, and we ask that you do not advertise it on social media or take other actions that would further compromise double-blind reviewing during the anonymity period.

- Note that, while you are not prohibited from making a non-anonymous version available online before the start of the anonymity period, this does make double-blind reviewing more difficult to maintain, and we, therefore, encourage you to wait until the end of the anonymity period if possible.

Citations and Comparison: If you are aware of previous research that appears sound and is relevant to your work, you should cite it even if it has not been peer-reviewed, and certainly if it influenced your own work. However, refereed publications take priority over unpublished work reported in preprints. Specifically:

You are expected to cite all refereed publications relevant to your submission, but you may be excused for not knowing about unpublished work (especially work that has been recently posted or is not widely cited).


In cases where a preprint has been superseded by a refereed publication, the refereed publication should be cited in addition to or instead of the preprint version.

Papers (whether refereed or not) appearing less than three months before the submission deadline are considered contemporaneous to your submission, and you are therefore not obliged to make detailed comparisons that require additional experimentation or in-depth analysis.



Acceptable submissions that require language (English) or organizational assistance will be flagged for mentoring and accepted with a recommendation to revise with the help of a mentor. An experienced mentor who has previously published in the SIGDIAL venue will then help the authors of these flagged papers prepare their submissions for publication.



In order to recognize significant advancements in dialogue/discourse science and technology, SIGDIAL 2021 will include the best paper awards. All papers at the conference are eligible for the best paper awards. A selection committee consisting of prominent researchers in the fields of interest will select the recipients of the awards.

General Chair: 

Haizhou Li, National University of Singapore, Singapore


Program Chairs:

Gina-Anne Levow, University of Washington, USA

Zhou Yu, Columbia University, USA


Publication Chair: 

Jessy Li, University of Texas at Austin, USA

Sponsorship Chair:

David Vandyke, Apple, UK


Mentoring Chair:

Nina Dethlefs, University of Hull, UK


Finance Chair: 

Yan Wu, Institute for Infocomm Research, Singapore


SIGdial President: 

Gabriel Skantze, KTH Royal Institute of Technology, Sweden


SIGdial Vice President:

Mikio Nakano, C4A Research Institute, Japan


SIGdial Secretary:

Vikram Ramanarayanan, Educational Testing Service (ETS) Research, USA


SIGdial Treasurer:

Ethan Selfridge, LivePerson, USA


SIGdial President Emeritus:

Jason Williams, Apple, USA


3-3-4(2021-08-02) Workshop Annotation, Recognition and Evaluation of Actions

AREA-II - Annotation, Recognition and Evaluation of Actions    ==========================================

Call for Papers

AREA- II will be an online event at the 32nd European Summer School in Logic, Language and Information - ESSLLI 2021. AREA-II is organized in the second ESSLLI week with plenary talks, posters and demonstrations. AREA-II is a SIGSEM-sponsored workshop. 

Date: 2 - 3 August 2021



AREA II is the follow up on the first AREA meeting at LREC 2018  ( There has recently been increased interest in modeling actions, as described by natural language expressions and gestures, and as depicted by images and videos. Additionally, action modeling has emerged as an important topic in robotics and HCI. The goal of the AREA II workshop is to gather and discuss advances in research areas where actions are paramount e.g., virtual embodied agents, robotics, HRI, human-computer communication, as well as modeling multimodal human-human interactions involving actions. Action modeling is an inherently multi-disciplinary area, involving contributions from computational linguistics, AI, semantics, robotics, psychology, and formal logic.  

While there has been considerable attention in the community paid to the representation and recognition of events (e.g., the development of ISO-TimeML and associated specifications, and the 4 Workshops on ?EVENTS: Definition, Detection, Coreference, and Representation?), the goals of this workshop are focused specifically on actions undertaken by embodied agents as opposed to events in the abstract. By concentrating on actions, we hope to attract those researchers working in computational semantics, gesture, dialogue, HCI, robotics, and other areas, in order to develop a community around action as a communicative modality where their work can be communicated and shared. This community will be a venue for the development and evaluation of resources regarding the integration of action recognition and processing in human-computer communication.

We invite submissions on foundational, conceptual, and practical issues involving modeling actions, as described by natural language expressions and gestures, and as depicted by images and videos. Relevant topics include but are not limited to:

- dynamic models of actions

- formal semantic models of actions

- affordance modeling

- manipulation action modeling

- linking multimodal descriptions and presentations of actions (image, text, icon, video)

- automatic action recognition from text, images, and videos

- communicating and performing actions with robots or avatars for joint tasks

- action language grounding

- evaluation of action models



First CfP: 8 April

Final CfP: 30 April 2021

Extended Deadline for paper submission: May 23, 2021

Review deadline: 16 June 2021

Notification of acceptance: 30 June 2021 

Deadline for camera-ready version: 11 July 2021 

Workshop Date: 2-3 August 2021



Three types of submissions are invited: 

- Research papers, describing original research; these can be either long (6-8 pages, not including references) or short (3-4 pages, not including references); 

- Project notes, describing recent, ongoing or planned projects (2-4 pages including references);

- Demonstration notes, accompanying demonstration of software, tools, or systems (2-4 pages including references).

We will decide whether to have an oral or poster presentation, depending on reviewer suggestions and the overall workshop schedule. 

Papers should be formatted following the common two-column structure as used by ACL. Please use style templates, which are available as an Overleaf template and can also be downloaded directly (Latex and Word). The templates themselves contain only specific notes (e.g., LaTeX notes in the .tex file). Please follow the paper formatting guidelines general to *ACL conferences available here. Similar to ACL 2021, initial submissions should be fully anonymous to ensure double-blind reviewing. 

Papers should be submitted via Easy chair  the AREA-II website ( will provide a link for submitting papers. 



For more information visit the workshop webpage at:

Or contact us at:,



Eren AksoyHalmstad University

Yiannis AloimonosUniversity of Maryland

Johan BosUniversity of Groningen

Harry BuntTilburg University

Simon DobnikUniversity of Gothenburg

Kristiina JokinenUniversity of Helsinki

Johan KwisthoutRadboud University Nijmegen

Alex LascaridesUniversity of Edinburgh

Andy Lucking Goethe-Universität Frankfurt am Main

Paul Piwek Open University

Gisela RedekerUniversity of Groningen

David TraumUSC Institute for Creative Technologies

Janina WildfeuerUniversity of Groningen

Florentin WörgötteGeorg-August University Göttingen



James Pustejovsky Brandeis University

Ielka van de SluisUniversity of Groningen





Ielka van der Sluis

Department of Communication and Information Sciences
Center for Language and Cognition Groningen
Faculty of Arts, University of Groningen         

Oude Kijk in ?t Jatstraat 26
9712 EK Groningen, the Netherlands
office: Harmoniegebouw 1312-428

phone office: +31 (0)50 363 5813
phone mobile: +31 (0)63 151 6041
phone secretary: +31 (0)50 363 5858

3-3-5(2021-08-14) 7th SIGKDD Workshop on Mining and Learning from Time Series (MiLeTS) 2021 Virtual conference

08-14) 7th SIGKDD Workshop on Mining and Learning from Time Series (MiLeTS) 2021
Aug 14th, 2021 - KDD Virtual Conference


Paper Submission Deadline: May 20th, 2021, 11:59PM Alofi Time
Author Notification: June 10th, 2021
Camera Ready Version: June 24th, 2021
Workshop: August 14th, 2021

MiLeTS is the premier KDD workshop on Mining and Learning from Time Series.

Time series data are ubiquitous. In domains as diverse as finance, entertainment, transportation, and health care, we observe a fundamental shift away from parsimonious, infrequent measurement to nearly continuous monitoring and recording. Rapid advances in diverse sensing technologies, ranging from remote sensors to wearables and social sensing, are generating rapid growth in the size and complexity of time series archives. Thus, although time series analysis has been studied extensively, its importance only continues to grow. What is more, modern time series data pose significant challenges to existing techniques (e.g., irregular sampling in hospital records and spatiotemporal structure in climate data). Finally, time series mining research is challenging and rewarding because it bridges a variety of disciplines and demands interdisciplinary solutions. Now is the time to discuss the next generation of temporal mining algorithms. The focus of MiLeTS workshop is to synergize the research in this area and discuss both new and open problems in time series analysis and mining. The solutions to these problems may be algorithmic, theoretical, statistical, or systems-based in nature. Further, MiLeTS emphasizes applications to high impact or relatively new domains, including but not limited to biology, health and medicine, climate and weather, road traffic, astronomy, and energy.

The MiLeTS workshop will discuss a broad variety of topics related to time series, including:
·       Time series pattern mining and detection, representation, searching and indexing, classification, clustering, prediction, forecasting, and rule mining.
·       BIG time series data.
·       Hardware acceleration techniques using GPUs, FPGAs and special processors.
·       Online, high-speed learning and mining from streaming time series.
·       Uncertain time series mining.
·       Privacy preserving time series mining and learning.
·       Time series that are multivariate, high-dimensional, heterogeneous, etc., or that possess other atypical properties.
·       Time series with special structure: spatiotemporal (e.g., wind patterns at different locations), relational (e.g., patients with similar diseases), hierarchical, etc.
·       Time series with sparse or irregular sampling, non-random missing values, and special types of measurement noise or bias.
·       Time series analysis using less traditional approaches, such as deep learning and subspace clustering.
·       Applications to high impact or relatively new time series domains, such as health and medicine, road traffic, and air quality.
·       New, open, or unsolved problems in time series analysis and mining.

Submission Guidelines
Submissions should follow the SIGKDD formatting requirements and will be evaluated using the SIGKDD Research Track evaluation criteria. Preference will be given to papers that are reproducible, and authors are encouraged to share their data and code publicly whenever possible. Submissions are strongly recommended to be no more than 4 pages, excluding references or supplementary materials (all in a single pdf). The appropriateness of using additional pages over the recommended length will be judged by reviewers. All submissions must be in pdf format using the workshop template (latex, word). Submissions will be managed via the MiLeTS 2021 EasyChair website:

Note on open problem submissions: To promote new and innovative research on time series, we plan to accept a small number of high-quality manuscripts describing open problems in time series analysis and mining. Such papers should provide a clear, detailed description and analysis of a new or open problem that poses a significant challenge to existing techniques, as well as a thorough empirical investigation demonstrating that current methods are insufficient.

COVID-19 Time Series Analysis Special Track: The COVID-19 pandemic is impacting almost everyone worldwide and is expected to have life-altering short and long-term effects. There are many potential applications of time series analysis and mining that can contribute to the understanding of this pandemic. We encourage the submission of high-quality manuscripts describing original problems, time-series datasets, and novel solutions for time series analysis and forecasting of COVID-19.

The review process is single-round and double-blind (submission files have to be anonymized). Concurrent submissions to other journals and conferences are acceptable. Accepted papers will be presented as posters during the workshop and listed on the website. Besides, a small number of accepted papers will be selected to be presented as contributed talks.

Any questions may be directed to the workshop e-mail address:

Paper Submission Deadline: May 20th, 2021, 11:59PM Alofi Time
Author Notification: June 10th, 2021
Camera Ready Version: June 24th, 2021
Workshop: August 14th, 2021

Organizing Committee
Sanjay Purushotham
University of Maryland, Baltimore County

Yaguang Li

Zhengping Che
Didi Chuxing

Steering Committee
Eamonn Keogh
University of California Riverside

Yan Liu
University of Southern California

Abdullah Mueen
University of New Mexico

Any questions may be directed to the workshop e-mail address:

3-3-6(2021-08-23) The European Signal Processing Conference (EUSIPCO), Dublin, Ireland

The European Signal Processing Conference (EUSIPCO) is the flagship conference of European Association for Signal Processing (EURASIP), and it is a great pleasure of the organizing committee to invite you to the 29th EUSIPCO organised in 2021 by Dublin Ireland. 

Technical scope 

We invite the submission of original, unpublished technical papers from all areas of signal processing including but not limited to: 

  • Audio and acoustic signal processing 
  • Speech and language processing 
  • Multimedia signal processing 
  • Signal processing theory and methods 
  • Sensor array and multichannel signal processing 
  • Signal processing for communications 
  • Radar and sonar signal processing 
  • Signal processing over graphs and networks 
  • Nonlinear signal processing 
  • Statistical signal processing 
  • Compressed sensing and sparse modelling 
  • Image and video processing 
  • Optimization methods 
  • Machine learning 
  • Bio-medical image and signal processing 
  • Signal processing for computer vision & robotics 
  • Computational imaging/ Spectral imaging 
  • Information forensics and security 
  • Signal processing for power systems 
  • Signal processing for education 
  • Bioinformatics and genomics 
  • Signal processing for big data 
  • Design/implementation of signal processing systems 
  • Signal processing for the internet of things 



Key dates  

  • Submission date: 22nd February 2021 (Extended) 
  • Notification of Acceptance: 20 April 2021 
  • Conference dates: 23-27 August 2021 

Accepted papers will be published in IEEE Xplore© & published Open Access by EURASIP. See  &  for formatting instructions.  

Follow Twitter @eusipco 2021  and LinkedIn 


Announcements mailing list

3-3-7(2021-08-25) Disfluency in Spontaneous Speech (DiSS) workshop (on line)

 Second Call for Papers

*The 10th edition of the Disfluency in Spontaneous Speech (DiSS) workshop will be held
online on August 25-26, 2021*. It will be followed by *a special day on (dis)fluency in
speech and language pathology on August 27, 2021*.

NEW important dates:
- April 9, 2021: Submission deadline
- May 22, 2021: Notification of acceptance
- August 25-27, 2021: Fully virtual workshop

Submissions are encouraged within the following fields: disfluency in spontaneous speech
- psychology, neuropsychology and neurocognition,
- psycholinguistics,
- linguistics, conversation analysis,
- computational linguistics, speech technology,
- gesture analysis,
- dialog systems,
- pathological speech disfluency,
- evolutionary aspects on speech production and perception

More information can be found at this URL:


3-3-8(2021-08-27) 4th International Workshop on the History of Speech Communication Research (HSCR) in Prague

We invite researchers across disciplines to participate in the 4th International Workshop on the History of Speech Communication Research (HSCR) in Prague.




The aim of the workshop is to bring together researchers interested in historical aspects of all areas of speech communication research. Contributions on any such topic will be welcome.

What is worth examining, among other things, is the approach of researchers to their material. The special focus will be on the link in linguistic signs between the form (sound) and the meaning (sense) in speech communication research. The phonetic endeavour was often claimed to concern only the form, while meaning was delegated to semanticians (affective psychology, pragmatics or semantics in broader sense). Studying the sound structure of human speech without a regard to communicative meanings is not only one-sided and incomplete, but also difficult to integrate into the wider scientific knowledge. The way researchers managed/refused to ignore meanings (functions) could be quite inspiring today.

Invited speakers are Angelika Braun from Trier University (Germany) with a talk entitled ?Leaving the ivory tower: How real-life events have impacted phonetics throughout history? and Tomá? Hoskovec, President of the Prague Linguistic Circle (Czech Rep.) with a talk on ?The relationship of meaning, sense and form throughout the history of European research?.

The proceedings will be published in the book series Studientexte zur Sprachkommunikation at TUDpress (Technical University Dresden).






Full-paper submission:

May 16, 2021

Notification of acceptance:

June 13, 2021

Camera-ready paper submission:

July 4, 2021


August 27-28, 2021


August 30 ? September 3, 2021





Jan Volín (, Institute of Phonetics, Charles University

Pavel ?turm (, Institute of Phonetics, Charles University


3-3-9(2021-08-30) Interspeech 2021 Special Session on the Multilingual and code-switching ASR challenges for low resource Indian languages, Brno, Czechia.
Announcing the Multilingual and code-switching ASR challenges for low resource Indian languages - Interspeech 2021 Special Session
Recently, there have been increasing interests in multilingual automatic speech recognition (ASR) where a speech recognition system is built to cater to multiple low resource languages by taking advantage of low amount of labeled corpora in multiple languages. On the other hand, with multilingualism becoming common in today?s world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different sub-tasks related to a total of seven Indian languages with constraints on the data available for acoustic modeling and language modeling.
This sub-task involves building a multilingual ASR system in six languages, namely, Hindi, Marathi, Odia, Telugu, Tamil, and Gujarati. The blind test set will comprise recordings from a subset (or all) of these six languages
This sub-task involves building a code-switching ASR system separately for Hindi-English and Bengali-English code-switched pairs. The blind test set will comprise recordings from these two code-switched language pairs.
Submissions to this special session should show results on one or both of the above mentioned tasks. Submissions on any topic related to building multilingual code-switching ASR are welcome. This includes (but is not limited to):
  • Acoustic modeling for multilingual ASR models
  • Language modeling for multilingual ASR models
  • Multilingual ASR model for code-switching
  • Language modeling for code-switching
  • Linguistically informed models for code-switching
Kalika Bali (Mircosoft Research)
Prasanta Kumar Ghosh (IISc Bangalore)
Raoul Nanavati (Navana Tech.)
Jai Nanavati (Navana Tech.)
Sirnivasa Raghavan (Navana Tech.)
Vivek Seshadri (Microsoft Research)
Preethi Jyothi (IIT Bombay)
Sunita Sarawagi (IIT Bombay)
Samarth Bharadwaj (IBM Research)
Ashish Mittal (IIT Bombay & IBM Research)
Shreya Khare (IBM Research)
For more details and participation, please visit
February 2, 2021 - Registration for the challenge opens
February 10, 2021 - Release training & test data
February 15, 2021 - Release baseline recipe
February 28, 2021 - Release blind test audio to participants
March 2, 2021 - Test trial upload begins
March 26, 2021 - Abstract submission deadline
March 26, 2021 - Final test trial upload deadline
April 2, 2021 - Interspeech final paper upload deadline
June 15, 2021 - Camera ready paper deadline
For any questions, write to

3-3-10(2021-08-30) The Fearless Steps Challenge(FSC) @ Interspeech 2021

ISCApad INTERSPEECH February 2021 February 10, 2021

The Fearless Steps Challenge(FSC)

TIMELINE: Challenge Start Date (Data Release): February 11th 2021

INTERSPEECH-2020 Papers dealing with FEARLESS STEPS deadline: April 2, 2021

Website Link:

Registration Link:





The Fearless Steps Initiative by UTDallas-CRSS led to the digitization, recovery, and diarization of 19,000 hours of original analog audio data, as well as the development of algorithms to extract meaningful information from this naturalistic data resource. As an initial step to motivate a stream-lined and collaborative effort from the speech and language community, UTDallas-CRSS is hosting a series of progressively complex tasks to promote advanced research on naturalistic “Big Data” corpora. This began with ISCA INTERSPEECH-2019: 'The FEARLESS STEPS Challenge: Phase 1 (FSC-P1)'. This first edition of this challenge encouraged the development of core unsupervised/semi-supervised speech and language systems for single-channel data with low resource availability, serving as the “First Step” towards extracting high-level information from such massive unlabeled corpora. This was followed with ISCA INTERSPEECH-2020 which held the Special Session for FEARLESS STEPS Challenge: Phase 2 (FSC-P2), which focused on developing supervised learning strategies for the 100 hour Challenge Corpus.

As a natural progression following the successful Inaugural Challenge FSC-P1 and FEARLESS STEPS Challenge FSC-P2, the FEARLESS STEPS Challenge: Phase 3 (FSC-P3) focuses on development of single-channel supervised learning strategies with an aim to test system generalizability to varying channel and mission data. FSC-P3 also provides an additional challenge task of Conversational Analysis, motivating researchers to work on natural language understanding and group dynamics analysis. FSC-P3 provides 80 hours of ground-truth data through Training and Development sets, with 20 hours of blind-set Apollo-11 evaluation data, 5 hours of unseen channel evaluation data and an additional 5 hours of blind-set Apollo-13 mission evaluation data. Based on feedback from the Fearless Steps participants, additional Tracks for streamlined speech recognition, speaker diarization, and conversational analysis have been included in the FS#3. The results for this Challenge will be presented at the ISCA INTERSPEECH-2021 Special Session. We encourage participants to explore any and all research tasks of interest with the Fearless Steps Corpus – with suggested Task Domains listed below. Research participants can however, also utilize the FSC-P3 corpus to explore additional problems dealing with naturalistic data, which we welcome as part of the special session.


Challenge Tasks in Fearless Steps Phase 3 (FSC-P3):

1. Speech Activity Detection (SAD)

2. Speaker Identification (SID)

3. Speaker Diarization:

3a. Track 1: Diarization using reference SAD

3b. Track 2: Diarization using system SAD

4. Automatic Speech Recognition (ASR):

4a. Track 1: ASR using reference Diarization

4b. Track 2: Continuous stream ASR

5. Conversational Analysis (CONV):

5a. Track 1: Hotspot Detection

5b. Track 2: Extractive Summarization



John H.L. Hansen (

Christopher Cieri (

Omid Sadjadi (

Aditya Joglekar (

Meena Chandra Shekar (


3-3-11(2021-08-31) DiCOVA Interspeech challenge 2021

Announcing the DiCOVA Interspeech challenge 2021 


The COVID-19 pandemic has resulted in more than 100 million infections, and more than 2 million casualties. The global crisis spans across 200 countries. Large scale testing, social distancing, and face masks have been critical measures to help contain the spread of the infection. Even with the onset of the vaccination programs, the WHO highlights large scale testing and precautionary measures must be followed for the next couple of years.  While the list of symptoms is regularly updated, it is established that in symptomatic cases COVID-19 seriously impairs normal functioning of the respiratory system. Does this alter the acoustic characteristics of breath, cough, and speech sounds produced through the respiratory system? This is an open question that we would like scientifically answer. A COVID-19 diagnosis methodology based on acoustic signal analysis, if successful, can provide a remote, scalable, and economical means for testing of individuals. This can supplement the existing nucleotides based COVID-19 testing methods, such as RT-PCR and RAT.


The DiCOVA Challenge is designed to find answers to the question by enabling participants to analyze an acoustic crowdsourced mobile based dataset gathered from COVID-19 positive and non-COVID-19 individuals. The findings will be presented in a special session at Interspeech 2021, the flagship conference of the global speech science and technology community, to be held in Brno from Aug 31-Sept 3, 2021. The timeliness, and the global societal importance of the challenge warrants focused effort from researchers across the globe, including from the fields of medical and respiratory sciences, mathematical sciences, and machine learning engineers. We look forward to your participation!

For more details and participation, please visit

Registration Opens: 5th Feb 2021

Data Release (Train and Dev): 15th Feb 2021 

Baseline System Release: 22nd Feb 2021 

Evaluation data and Leaderboard active: 1st Mar 2021 

Final evaluation and Report submission: 21st Mar 2021 

Interspeech Abstract submission: 26th Mar 2021 

Interspeech Paper submission: 2nd Apr 2021

Any questions can be directed to 

3-3-12(2021-09-04) First Shared Task on Automatic Minuting***AutoMin @ Interspeech 2021***

***First Shared Task on Automatic Minuting***

***AutoMin @ Interspeech 2021***

When most of our interactions went virtual, the need for automatic support for the smooth running of the online events such as project meetings became more intense. Summarizing meeting contents is one of them. We propose AutoMin, the First Shared Task on Automatic Minuting of meeting proceedings. With this shared task, we would invite the speech and natural language processing community to investigate the challenges of automatic minuting with real meeting data in two different settings: technical project meetings (both in English and Czech) and parliamentary proceedings (English). AutoMin is an ISCA-sponsored Interspeech 2021 satellite event. AutoMin 2021 will be a full-virtual event.





We propose one main task and two subsidiary tasks. The subsidiary tasks are optional.

  • Main Task A: The main task consists of automatically creating minutes from multiparty meeting transcripts. The generated minute would be evaluated both via automatic and manual metrics.

  • Task B: Given a pair of meeting transcripts and minutes, the task is to identify whether the minutes belong to the transcript. During our data preparation from meetings on similar topics, we found that this task could be challenging given the similarity in various named entities.

  • Task C: Given a pair of minutes, the task is to identify whether the two minutes belong to the same or different meetings. This sub-task is important as we want to uncover how minutes created by two different persons for the same meeting may differ in content and coverage.



All participants should register using the following link: 


***Data Usage Form***

Please send the signed data usage form to Tirthankar Ghosal at <> along with your Github id/email id to get access to the training data(mandatory)

***Important Dates***

Registration and CfP

May 08, 2021

Training and Dev Set Data Available

May 15, 2021

Test Data Available

June 15, 2021

System Run and Report Submission

July 15, 2021

Result Announcement

  August 15, 2021

Camera Ready Submission

August 25, 2021

Event Date

September 4, 2021

Invited Paper submission to Information Journal




All teams are required to submit a brief technical report describing their method. Please submit using the Interspeech 2021 paper template ( All reports must be a minimum of 2 pages and a maximum of 4 pages excluding references. Reports must be written in English. The proceedings will be hosted at the ISCA archive.

Selected authors would be additionally invited to submit a full paper to a special issue of the Information Journal by MDPI (



Tirthankar Ghosal, UFAL, Charles University, Czech Republic

Muskaan Singh, UFAL, Charles University, Czech Republic

Anja Nedoluzhko, UFAL, Charles University, Czech Republic

Ond?ej Bojar, UFAL, Charles University, Czech Republic



Tirthankar Ghosal at <>


3-3-13(2021-09-06) 14th WORKSHOP ON BUILDING AND USING COMPARABLE CORPORA (online) (updated)


Co-located with RANLP 2021 (online)

Monday, September 6, 2021

Workshop website:

RANLP website:


* Pushpak Bhattacharyya, Indian Institute of Technology Bombay

* Tomas Mikolov, Czech Institute of Informatics, Robotics and Cybernetics
* Sujith Ravi, Amazon Alexa AI



In the language engineering and the linguistics communities, research in comparable corpora has been motivated by two main reasons. In language engineering, on the one hand, it is chiefly motivated by the need to use comparable corpora as training data for statistical NLP applications such as statistical and neural machine translation or cross-lingual retrieval. In linguistics, on the other hand, comparable corpora are of interest because they enable cross-language discoveries and comparisons. It is generally accepted in both communities that comparable corpora consist of documents that are comparable in content and form in various degrees and dimensions across several languages. Parallel corpora are on the one end of this spectrum, unrelated corpora on the other.

Comparable corpora have been used in a range of applications, including Information Retrieval, Machine Translation, Cross-lingual text classification, etc.  The linguistic definitions and observations related to comparable corpora can improve methods to mine such corpora for applications of statistical NLP, for example to extract parallel corpora from comparable corpora for neural MT. As such, it is of great interest to bring together builders and users of such corpora.


This year our special topic is 'Neural Networks in Comparable Corpora Research'. But we solicit contributions on all topics related to comparable (and parallel) corpora, including but not limited to the following:

Building Comparable Corpora:

* Automatic and semi-automatic methods
* Methods to mine parallel and non-parallel corpora from the web
* Tools and criteria to evaluate the comparability of corpora
* Parallel vs non-parallel corpora, monolingual corpora
* Rare and minority languages, across language families
* Multi-media/multi-modal comparable corpora

Applications of comparable corpora:

* Human translation
* Language learning
* Cross-language information retrieval & document categorization
* Bilingual and multilingual projections
* Machine translation
* Writing assistance
* Machine learning techniques using comparable corpora

Mining from Comparable Corpora:

* Cross-language distributional semantics, word embeddings and pre-trained multilingual transformer models
* Extraction of parallel segments or paraphrases from comparable corpora
* Methods to derive parallel from non-parallel corpora (e.g. to provide for low-resource languages in neural machine translation)
* Extraction of bilingual and multilingual translations of single words and multi-word expressions, proper names, and named entities from comparable corpora
* Induction of morphological, grammatical, and translation rules from comparable corpora
- Induction of multilingual word classes from comparable corpora


July 17, 2021: Paper submission deadline
July 31, 2021: Notification of acceptance
August 31, 2021: Camera ready final papers
September 6, 2021: Workshop date

For updates see the workshop website at


The workshop proceedings will be published in the ACL Anthology.

The link for participation in the online workshop will be communicated to registered participants in due time.

Workshop fees are 45 Euros for presenters (30 Euros for student presenters) and 15 Euros for non-presenters. For further details see


Please follow the style sheet and templates provided for the main conference at
Papers should be submitted as a PDF file using the START conference manager at
Submissions must describe original and unpublished work and range from 4 to 8 pages plus unlimited references.
Reviewing will be double blind, so the papers should not reveal the authors' identity. Accepted papers will be published in the workshop proceedings, which will be included in the ACL Anthology.

Double submission policy: Parallel submission to other meetings or publications is possible but must be immediately notified to the workshop organizers by e-mail.

For further information and updates see the BUCC 2021 website:

In case of questions, please contact Reinhard Rapp: reinhardrapp (at) gmx (dot) de


* Reinhard Rapp (Athena R.C.; Magdeburg-Stendal University of Applied Sciences; University of Mainz, Germany), chair and contact person: reinhardrapp (at) gmx (dot) de
* Serge Sharoff (University of Leeds, United Kingdom)
* Pierre Zweigenbaum (Université Paris-Saclay, CNRS, LISN, Orsay, France)


* Ahmet Aker (University of Duisburg-Essen, Germany)
* Ebrahim Ansari (Institue for Advanced Studies in Basic Sciences, Iran)
* Thierry Etchegoyhen (Vicomtech, Spain)
* Hitoshi Isahara (Otemon Gakuin University, Japan)
* Kyo Kageura (The University of Tokyo, Japan)
* Natalie Kübler (CLILLAC-ARP, Université de Paris, France)
* Philippe Langlais (Univerité de Montréal, Canada)
* Yves Lepage (Waseda University, Japan)
* Emmanuel Morin (Université de Nantes, France)
* Dragos Stefan Munteanu (RWS, USA)
* Reinhard Rapp (Magdeburg-Stendal University of Applied Sciences and University of Mainz, Germany)
* Nasredine Semmar (CEA LIST, Paris, France)
* Serge Sharoff (University of Leeds, UK)
* Richard Sproat (OGI School of Science & Technology, USA)
* Tim Van de Cruys (KU Leuven, Belgium)
* Pierre Zweigenbaum (Université Paris-Saclay, CNRS, LISN, Orsay, France)

3-3-14(2021-09-06) 24th International Conference on Text, Speech and Dialogue (TSD 2021), Olomouc, Czech Republic

                      TSD 2021 - LAST CALL FOR PAPERS

The twenty-fourth International Conference on Text, Speech and Dialogue (TSD 2021)
              Olomouc, Czech Republic, September 06-09, 2021


Deadline for submission is approaching fast (April 18, 2021) and it is not
going to be postponed.

We work on a very tight schedule. However, if you absolutely need a few
extra days, please submit an abstract, make a clear note of when you submit
the final version, and submit it as a common document.


The TSD 2021 conference will be accompanied by one-day satellite workshops
or project meetings with organizational support from the TSD organizing
committee. The workshops and demonstrations will take place in physical
and/or virtual form, depending on the situation with COVID-19.

Please, see the separate call for Workshops and Demonstrations.

Workshop and demonstration proposals can be sent via the submission form


As the situation in September 2021 cannot be easily predicted, the TSD 2021
organizing committee is ready to organize a virtual conference, if necessary.

    * PC members have good experience with it since TSD 2020,
    * A virtual conference would mean significantly decreased conference fees.
    * If the majority of participants could travel to the Czech Republic,
      the onsite mode of the conference is preferred. For others, there
      would be special virtual sessions. Organizers will record all the

All measures have been taken to ensure that the organization of the TSD
2021 conference in September 2021 is not threatened by the COVID-19


* Keynote speakers:

    Olga Vechtomova (University of Waterloo, Canada)
    Kate Knill (University of Cambridge, UK)
    Lucie Flek (Technical University of Darmstadt, Germany)
    Ivan Vulic (University of Cambridge, UK)

* The TSD 2021 conference is officially recognized as an INTERSPEECH 2021
  satellite event.
* The TSD 2021 conference is supported by the International Speech
  Communication Association (ISCA). It holds the status of an ISCA
  Supported Event.
* The TSD book of proceedings is traditionally published by Springer and
  regularly listed in all major citation databases: Thomson Reuters
  Conference Proceedings Citation Index, DBLP, SCOPUS, EI, INSPEC,
* TSD offers a high-standard transparent review process - double blind,
  final reviewers' discussion.
* TSD 2021 is going to take place in the beautiful city of Olomouc, Czech
* The conference is organized in cooperation with the Faculty of Arts,
  Palacky university, Olomouc.
* TSD provides an all-service package (conference access and material, all
  meals, social events, etc.) for an easily affordable fee.


April 18, 2021 ........... Deadline for submission of contributions
May 21, 2021 ............. Notification of acceptance or rejection
May 31, 2021 ............. Deadline for submission of camera-ready papers

September 06-09, 2021 .... TSD 2021 conference time

TSD 2021 is going to take place in the beautiful city of Olomouc, Czech
Republic. Thus, it is nicely colocated with Interspeech 2021 which is going
to be held in Brno, Czech Republic, a week earlier (August 30 - September
3, 2021). Olomouc is only 77 km (48 mi) away from Brno (30-45 min by car,
1 hour by public transport).


The TSD series has evolved as a prime forum for interaction between
researchers in both spoken and written language processing from all over
the world. Proceedings of the TSD conference form a book published by
Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI)
series. The TSD proceedings are regularly indexed by Thomson Reuters
Conference Proceedings Citation Index. LNAI series are listed in all major
citation databases such as DBLP, SCOPUS, EI, INSPEC, or COMPENDEX.

The proceedings will be provided on flash drives in the form of navigable
content. Printed books will be available for an extra fee.


Topics of the 24th conference will include (but are not limited to):

    Speech Recognition (multilingual, continuous, emotional speech,
    handicapped speaker, out-of-vocabulary words, alternative way of
    feature extraction, new models for acoustic and language modeling).

    Corpora and Language Resources (monolingual, multilingual, text, and
    spoken corpora, large web corpora, disambiguation, specialized
    lexicons, dictionaries).

    Speech and Spoken Language Generation (multilingual, high fidelity
    speech synthesis, computer singing).

    Tagging, Classification and Parsing of Text and Speech (multilingual
    processing, sentiment analysis, credibility analysis, automatic text
    labeling, summarization, authorship attribution).

    Semantic Processing of Text and Speech (information extraction,
    information retrieval, data mining, semantic web, knowledge
    representation, inference, ontologies, sense disambiguation, plagiarism

    Integrating Applications of Text and Speech Processing (machine
    translation, natural language understanding, question-answering
    strategies, assistive technologies).

    Automatic Dialogue Systems (self-learning, multilingual,
    question-answering systems, dialogue strategies, prosody in dialogues).

    Multimodal Techniques and Modeling (video processing, facial animation,
    visual speech synthesis, user modeling, emotion and personality


All programme committee members are listed on the conference web pages


The official language of the event is English, however, papers on issues
related to text and speech processing in languages other than English are
strongly encouraged.


Olomouc is a beautiful place on the Morava river with more than
a thousand-year-long history. Once a capital of Moravia - one of the three
historical Lands of the Bohemian Crown - nowadays, it still somehow waits
to be rediscovered. The world-renowned tourist guide Lonely Planet alerted
to this fact by putting Olomouc onto the list of TOP 10 tourist
destinations not to be missed during a visit to Europe. It even claimed
Olomouc is one of the most unappreciated destinations in the Czech

By its beauty, Olomouc can, however, easily compete with not only Prague
but any other most sought spots around Europe. It certainly deserves our

One can find there the second most important urban conservation zone in the
Czech Republic, surrounded by splendorous parks, an incredible
concentration of ecclesiastical structures, UNESCO-protected monuments, and
even a horolog with a history maybe more interesting than the Prague one.
All together safe from the neverending bustle of large cities.

The most important monument in Olomouc is the Holy Trinity Column standing
in the central square. It represents the largest group of Baroque statues
in one structure in Central Europe. Apart from many historical buildings
such as Olomouc castle with the gothic cathedral of St. Wenceslas or the
former Olomouc fortress, another interesting point about Olomouc is the
astronomical clock, designed in the spirit of Socialist Realism.

The city of Olomouc has a convenient location close to the geographic
centre of Moravia (a historical region in the east of the Czech Republic),
on the banks of the river Morava. The place forms an important highway and
railroad junction; thus, it is easily accessible using both individual and
public means of transport.

Olomouc lies 260 km (162 mi) eastwards from the Czech capital Prague, and
210 km (130 mi) from both the Slovakian capital Bratislava and the Austrian
capital Vienna. The closest international airports are 77 km (48 mi) away
in Brno, and 202 km (126 mi) away in Katowice in Poland.

We are very excited about the fact that the TSD 2021 is going to take place
in such a fabulous, unique city rich in history as Olomouc.


The conference is organized by the Faculty of Applied Sciences, University
of West Bohemia, Pilsen; the Faculty of Informatics, Masaryk University,
Brno; and the Faculty of Arts, Palacky University, Olomouc.


Faculty of Arts, Palacky University, Olomouc
Biskupske nam. 842/1
77900 Olomouc
Czech Republic


The preferred way of contacting the conference organizing committee is
writing an e-mail to:

    Ms Lucie Tauchenova, TSD 2021 Conference Secretary
    Phone: +420 730 851 103

All paper correspondence regarding the conference should be addressed to:

    TSD 2021 - Katedra informatiky a vypocetni techniky

    Fakulta aplikovanych ved
    Zapadoceska univerzita v Plzni
    Univerzitni 8
    CZ-306 14 Plzen
    Czech Republic

    Fax: +420 377 632 402 - Please, mark the faxed material with large
    capitals 'TSD21' on top.

TSD 2021 conference website:




3-3-15(2021-09-06) TSD 2021 CALL FOR WORKSHOPS AND DEMONSTRATIONS, Olomouc, Czech Republic


The twenty-fourth International Conference on Text, Speech and Dialogue (TSD 2021)
              Olomouc, Czech Republic, September 06-09, 2021


The TSD 2021 Organizing Committee invites you to submit proposals for
workshops and demonstrations using forms given below.

The TSD 2021 conference will be accompanied by one-day satellite workshops
and demonstrations on topics related to the general theme of the conference
with organizational support from the TSD organizing committee.


The role of workshops is to provide a setting for focused, intensive
scientific exchange among researchers and engineers interested in
a specific topic. As such, workshops are the primary venues for the
exploration of emerging ideas as well as for the discussion of novel
aspects of established research topics. Recommended workshop length is half
day or full day.


The role of demonstrations is to provide an extensive amplification of
papers presented at the TSD or stand-alone demonstrations of software or
hardware. Demonstrations offer an opportunity to showcase not only a novel
technology (software & hardware) but also interactive applications of
learning algorithms, dialog and conversational AIs, learning from
demonstration, real-time visualization of learning models etc.

Interaction with the audience during the demonstration is a critical
element. Therefore, the creativity of demonstrators to propose new ways in
which interaction and engagement can fully leverage this year's conference
will be particularly relevant for the selection. Recommended length of
a demonstration is 15 minutes up to  an hour.


The TSD organizing committee requires proposals for workshops and
demonstrations on research topics of interest to TSD 2021 attendees.
For more information regarding the conference topics please visit the
conference website here.


The workshops and demonstrations will take place in physical and/or virtual
form, depending on the situation with COVID-19.

We do hope to be able to have a physical conference. Nevertheless, we can
confirm that, in any scenario, TSD 2021 will provide the opportunity to
participate virtually and with a reduced registration pricing that factors
out local costs (e.g. coffee breaks, lunches, social events). This applies
also for workshops and demonstrations.


April 18, 2021 ........... Deadline for workshop proposals
May 31, 2021 ............. Deadline for demonstration proposals

September 06-09, 2021 .... TSD 2021 conference time

Earlier proposal submission is highly preferred for the workshop
propagation to be included in the conference Call for Papers and on the
conference website.


TSD 2021 does not offer separate workshop and demonstration fees. All
participants are expected to register at the main conference. All main
conference participants can attend an open workshop. However workshop
organizers can set a separate fee..

For more information regarding the conference fees visit the conference
website here.


Workshop and demonstration proposals can be sent via the submission form


Each workshop and demonstration proposal will be evaluated according to the
relevance of its topic, the expertise and experience of the workshop
organizers, and the workshop's potential for attracting participants and
generating useful results.

At least one author of each accepted proposal must register and attend TSD
2021 in order for the workshop to be accepted and the summary of the
workshop published.


All proposal submissions will be subject to review by the TSD organising
committee. After the notification of acceptance, the submitters will be
contacted for the practical details. In order to include the selected
submissions to the conference a full registration of the submitter is
recommended before the deadline for submission of contributions to the
conference, i.e. April 18, 2021.


Faculty of Arts, Palacky University, Olomouc
Biskupske nam. 842/1
77900 Olomouc
Czech Republic


The preferred way of contacting the conference organizing committee is
writing an e-mail to:

    Ms Lucie Tauchenova, TSD 2021 Conference Secretary
    Phone: +420 730 851 103

All paper correspondence regarding the conference should be addressed to:

    TSD 2021 - Katedra informatiky a vypocetni techniky

    Fakulta aplikovanych ved
    Zapadoceska univerzita v Plzni
    Univerzitni 8
    CZ-306 14 Plzen
    Czech Republic

    Fax: +420 377 632 402 - Please, mark the faxed material with large
    capitals 'TSD 2021' on top.

 TSD 2021 conference website:


3-3-16(2021-09-07) CfP Text Mining and Applications (TeMA?21) Track of EPIA?21, Lisbon, Portugal

Call for Papers 

Text Mining and Applications (TeMA?21) Track of EPIA?21


TeMA 2021 will be held at the 20th Portuguese Conference on Artificial Intelligence (EPIA 2021) taking place at Lisbon, Portugal, from 7th to 9th September 2021. This track is organized under the auspices of the Portuguese Association for Artificial Intelligence (APPIA). EPIA 2021 URL: :

This announcement contains the following information:

[1] Track description; [2] Topics of interest; [3] Important dates; [4] Paper submission; [5] Track fees; [6] Organizing Committee; [7] Program Committee and [8] Contacts.

[1] Track Description

The 9th Track of Text Mining and Applications (TeMA 2021) is a forum for researchers working in Human Language Technologies, i.e. Natural Language Processing (NLP), Computational Linguistics (CL), Natural Language Engineering (NLE), Text Mining (TM), Information Retrieval (IR), and related areas.

              The most natural form of sharing knowledge is indeed through textual documents. Especially on the Web, a huge amount of textual information is openly published every day, on many different topics and written in natural language, thus offering new insights and many opportunities for innovative applications of Human Language Technologies.

              Following recent advances in general IA sub-fields such as NLP, Machine Learning (ML) and Deep Learning (DL), text mining is now even more valuable as tool for bridging the gap between language theories and effective use of natural language contents, for harnessing the power of semi-structured and unstructured data, and to enable important applications in real-world heterogeneous environments. Both hidden and new knowledge can be discovered by using text mining methods, at multiple levels and in multiple dimensions, and often with high commercial value.

Authors are invited to submit their papers on any of the issues identified in section [2]. Revision of the papers will be double-blind by the members of the Program Committee. All accepted papers will be published by Springer in a volume of Springer?s Lecture Notes in Artificial Intelligence (LNAI) corresponding to the proceedings of the 20th EPIA Conference on Artificial Intelligence, EPIA 2021.


[2] Topics of Interest

TM, NLP, and Social Media Content Analysis

  • Entity Recognition and Disambiguation
  • Relation Extraction
  • Analysis of Opinions, Emotions and Sentiments
  • Text Clustering and Classification
  • Machine Translation
  • Summarization
  • Word Sense Disambiguation
  • Co-Reference Resolution
  • Language Modeling
  • Syntax and Parsing
  • Distributional Models and Semantics
  • Multi-Word Units
  • Lexical Knowledge Acquisition
  • Spatio-Temporal Text Mining
  • Entailment and Paraphrases
  • Natural Language Generation
  • Language Resources: Acquisition and Usage
  • Cross-Lingual Approaches
  • Algorithms and Data Structures for Text Mining


  • Information Retrieval and Information Extraction
  • Question-Answering and Dialogue Systems
  • Text-Based Prediction and Forecasting
  • Web Content Annotation
  • Computational Social Science
  • Computational Journalism
  • Health and Well-being
  • Big Data Analysis

 [3] Important dates

Paper submission deadline: April 15, 2021

Paper acceptance notification: May 31, 2021

Camera-ready deadline: June 15, 2021

                      EPIA Conference: September 7-9, 2021(Lisbon, Portugal)

[4] Paper submission

Submissions must be full technical papers on substantial, original, and previously unpublished research. Papers can have a maximum length of 12 pages. All papers should be prepared according to the formatting instructions of Springer LNAI series. Authors should omit their names from the submitted papers, and should take reasonable care to avoid indirectly disclosing their identity. References to own work may be included in the paper, as long as referred to in the third person. All papers should be submitted in PDF format through the conference management website at:

Authors should consult Springer?s authors? guidelines and use their proceedings templates, either for LaTeX or for Word, for the preparation of their papers. Springer encourages authors to include their ORCIDs in their papers. In addition, the corresponding author of each paper, acting on behalf of all of the authors of that paper, must complete and sign a Consent-to-Publish form. The corresponding author signing the copyright form should match the corresponding author marked on the paper. Once the files have been sent to Springer, changes relating to the authorship of the papers cannot be made.


[5] Track Fees:

 Track participants must register at the main EPIA 2021 conference.


[6] Organizing Committee:

Joaquim Silva, DI ? FCT/UNL, Quinta da Torre, 2829-516 Caparica, Portugal (Contact person).

Pablo Gamallo, Universidade de Santiago de Compostela, Praza do Obradoiro, 0, 15705 Santiago de Compostela, A Coruña, Spain.

Paulo Quaresma, DI ? Uviversidade de Évora, Largo dos Colegiais 2, 7000-645 Évora, Portugal.

Irene Rodrigues., DI ? Uviversidade de Évora, Largo dos Colegiais 2, 7000-645 Évora, Portugal


[7] Program Committee:

Adam Jatowt ? Universit of Kioto, Japan

Alberto Diaz ? Universidade Complutense de Madrid, Spain

Alberto Simões ? Algoritmi Center - University of Minho, Portugal

Alexandre Rademaker ? IBM / FGV, Brazil

Altigran Silva ? Universidade Federal do Amazonas, Brasil

Antoine Doucet ? University of Caen, France

António Branco ? Universidade de Lisboa, Portugal

Béatrice Daille ? University of Nantes, France

Bruno Martins ? Instituto Superior Técnico ? Universidade de Lisboa, Portugal

Eric de La Clergerie ? INRIA, France

Fernando Batista ? Instituto Universitário de Lisboa, Portugal 

Francisco Couto ? Faculdade de Ciências ? Universidade de Lisboa, Portugal

Gabriel Pereira Lopes ? Faculdade de Ciências e Tecnologia ? Universidade Nova de Lisboa, Portugal

Gaël Dias ? University of Caen Basse-Normandie

Hugo Oliveira ? Universidade de Coimbra, Portugal

Iñaki Vicente - Language Technology, Elhuyar Foundation

Irene Rodrigues ? Universidade de Évora, Portugal

Jesús Vilares ? University of A Coruña, Spain

Joaquim Ferreira da Silva ? Faculdade de Ciências e Tecnologia ? Universidade Nova de Lisboa

Katerzyna Wegrzyn-Wolska ? ESIGETEL, France

Luisa Coheur ? Universidade Técnica de Lisboa, Portugal

Manuel Vilares Ferro ? University of Vigo, Spain

Marcos Garcia - Universidade da Coruña, Spain

Mário Silva ? Instituto Superior Técnico ? Universidade de Lisboa, Portugal

Miguel Alonso ? Universidade da Coruña, Spain

Pablo Gamallo ? Faculdade de Filologia, Santiago de Compustela, Spain

Patricia Martín-Rodilla ? Universidade da Coruña, Spain

Paulo Quaresma ? Universidade de Évora, Portugal

Pavel Brazdil ? University of Porto, Portugal

Renata Vieira ? Universidade de Évora, Portugal

Sérgio Nunes ? Faculdade de Engenharia ? Universidade do Porto, Portugal


[8] Contacts

Joaquim Francisco Ferreira da Silva, DI/FCT/UNL, Quinta da Torre, 2829?516, Caparica, Portugal. Tel: +351 21 294 8536 (ext. 10732) ? Fax: +351 21 294 8541 ? E?mail: jfs [at]fct [dot] unl [dot] pt



3-3-17(2021-09-08) IEEE 4th International Conference on Multimedia Information Processing and Retrieval (MIPR 2021), Tokyo, Japan (Rescheduled)

IEEE 4th International Conference on
Multimedia Information Processing and Retrieval (MIPR 2021)

   Rescheduled September 8-10
  Tokyo, Japan.
  Sponsored by IEEE TCMC. Supported by IEICE, IPSJ, ITE.

Huge amounts of multimedia data are increasingly available and the knowledge of spatial and/or temporal phenomena becomes critical for many applications, which requires techniques for the processing, analysis, search, mining, and management of multimedia data. The 4th IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE-MIPR 2021) will take place in Tokyo, Japan on September 8-10, 2021. The conference will provide a forum for original research contributions and practical system design, implementation, and applications of multimedia information processing and retrieval. The target audiences will be university researchers, scientists, industry professionals, software engineers and graduate students who need to become acquainted with new theories and technologies in multimedia information processing and retrieval. MIPR 2021 is now inviting submissions of regular research papers, demo papers, workshop proposals, special session proposals, and tutorial proposals. Please refer to the detail of each category in the following.

- IEEE 3rd MIPR 2020 @ Shenzhen: 19.5% (Acceptance Rate)
- IEEE 2nd MIPR 2019 @ San Jose: 19.5% (Acceptance Rate)
- IEEE 1st MIPR 2018 @ Miami   : 19.5% (Acceptance Rate)
- 12 years of MIPR (workshop) in conjunction with IEEE ISM.


- 08-10 Sept, 2021: Conference dates.

*Call for Regular Papers*

IEEE MIPR 2021 will take place in Tokyo, Japan on Sep 8-10, 2021. The conference will provide a forum for original research contributions and practical system design, implementation, and applications of multimedia information processing and retrieval.

Topics of interest include, but are not limited to:

* Multimedia Retrieval
- Multimedia Search and Recommendation
- Web-Scale Retrieval
- Relevance Feedback, Active/Transfer Learning
- 3D and sensor data retrieval
- Multimodal Media (images, videos, texts, graph/relationship) Retrieval
- High-Level Semantic Multimedia Features

* Machine Learning/Deep Learning/Data Mining
- Deep Learning in Multimedia Data and / or Multimodal Fusion
- Deep Cross-Learning for Novel Features and Feature Selection
- High-Performance Deep Learning (Theories and Infrastructures)
- Spatio-Temporal Data Mining

* Content Understanding and Analytics
- Multimodal/Multisensor Integration and Analysis
- Effective and Scalable Solution for Big Data Integration
- Affective and Perceptual Multimedia
- Multimedia/Multimodal Interaction Interfaces with humans

* Multimedia and Vision
- Multimedia Telepresence and Virtual/Augmented/Mixed Reality
- Visual Concept Detection
- Object Detection and Tracking
- 3D Modeling, Reconstruction, and Interactive Applications

* Networks for Multimedia Systems
- Internet Scale System Design
- Information Coding for Content Delivery

* Systems and Infrastructures
- Multimedia Systems and Middleware
- Software Infrastructure for Data Analytics
- Distributed Multimedia Systems and Cloud Computing

* Data Management
- Multimedia Data Collections, Modeling, Indexing, or Storage
- Data Integrity, Security, Protection, Privacy
- Standards and Policies for Data Management

* Novel Applications
- Multimedia applications for health and sports
- Multimedia applications for culture and education
- Multimedia applications for fashion and living
- Multimedia applications for security and safety

*Internet of Multimedia Things
- Real-Time Data Processing
- Autonomous Systems such as Driverless Cars, Robots, and Drones
- Mobile and Wearable Multimedia

and others.

**Paper Submission**
The conference will accept regular papers (6 pages plus reference pages). Authors are encouraged to compare their approaches, qualitatively or quantitatively, with existing work and explain the strength and weakness of the new approaches. We are planning to invite selected submissions to journal special issues.

**Important Dates**
- Paper submission deadline: October 2, 2020
- Notification of acceptance: December 18, 2020
- Camera-ready deadline: January 8, 2021

*Call for Demo Papers*

IEEE MIPR 2021 organizing committee invites proposals for technical demonstrations to be presented in conjunction with the conference. Technical Demonstrations will show leading edge work in any area of multimedia information retrieval. Demonstrations offer the opportunity to present and receive feedback on live working systems in an informal setting. Submissions are particularly encouraged in the following areas with emphasis on multimedia information retrieval, but not limited to:

### Multimedia information Retrieval
* Multimedia Search and Recommendation
* Web-Scale Retrieval
* Relevance Feedback
* Active/Transfer Learning
* 3D and Sensor Data Retrieval
* Multimodal Media (images, videos, texts, graph/relationship) Retrieval
* High-Level Semantic Multimedia Features
* Summarization
* Personalized Retrieval
* Browsing History
* Fuzzy Retrieval
* Accuracy Measures for Retrieval

### Machine Learning/Deep Learning/Data Mining in Multimedia
* Deep Learning in Multimedia Data and/or Multimodal Fusion
* Deep Cross-Learning for Novel Features and Feature Selection
* High-Performance Deep Learning (Theories and Infrastructures)
* Spatio-Temporal Data Mining

### Content Understanding and Analytics in Multimedia
* Multimodal/Multisensor Integration and Analysis
* Effective and Scalable Solution for Big Data Integration
* Affective and Perceptual Multimedia
* Multimedia/Multimodal Interaction Interfaces with humans
* Bias and Fairness in Multimedia Analysis

### Multimedia and Vision
* Multimedia Telepresence and Virtual/Augmented/Mixed Reality
* Visual Concept Detection
* Object Detection and Tracking
* 3D Modeling, Reconstruction, and Interactive Applications

### Fake Multimedia
* Image/Video Forensics
* Forgery Detection
* Multimedia Content Protection

### Multimedia Information Systems and Infrastructures
* User Interface
* Query-By-Retrieval Methods
* Retrieval Paradigms
* Novel Interfaces for Retrieval
* Multimedia Systems and Middleware
* Telepresence and Virtual/Augmented/Mixed Reality
* Software Infrastructure for Data Analytics
* Distributed Multimedia Systems and Cloud Computing
* GPU-based Retrieval

### Multimedia Data Management
* Multimedia Data Collections, Modeling, Indexing, or Storage
* Data Integrity, Security, Protection, Privacy
* Standards and Policies for Data Management
* Spatio-Temporal Modeling and Retrieval

### Novel Applications in Multimedia
* Multimedia Forensics and Security
* Urban planning and emergency responses
* Environmental monitoring
* Education (using Multimedia for Education or Education about Multimedia)
* Social Networks (multimedia content)
* Multimedia Information Retrieval from Scientific Databases
* Multimedia for Healthcare and Medicine

### Internet of Multimedia Things
* Real-Time Data Processing
* Autonomous Systems such as Driverless Cars, Robots, and Drones
* Mobile and Wearable Multimedia

The written and spoken language of IEEE MIPR 2021 is English. For technical demonstrations, authors should submit:

* a 4-page manuscript in double-column IEEE format including the authors’ names and affiliations, following the submission guidelines available on the IEEE MIPR 2021 web page
* a short abstract electronically, following the submission guidelines available on the IEEE MIPR 2021 web page
* a presentation/video, which can be a Microsoft PowerPoint presentation, a Flash presentation, an MPEG/WMV video clip, or a link on for the corresponding presentation on Social Media (e.g., vimeo, YouTube) not more than five minutes long.

Please create a single zip archive of all files, and upload it to the paper submission system. Only electronic submissions will be accepted. All technical demonstration papers should be in Adobe portable document format (PDF). The Conference Proceedings will be published by the IEEE Computer Society Press and be available for online access via IEEEXplore.

All submissions will be peer-reviewed to ensure quality. Demonstrators will be provided with space and access to a local network, however, demos should not rely on Internet access. The participants will be required to provide their own computing equipment and any additional network, display, or other specific hardware needed for the demonstration.

**Important Dates**

* Paper submission deadline: November 6, 2020
* Notification of acceptance: December 25, 2020
* Camera-ready deadline: January 8, 2021

*Call for Tutorials*

IEEE MIPR 2021 invites proposals for tutorials to be held on March 22 or March 24, 2021 (tentative date). We welcome 1.5 hours or 3 hours tutorial. Each tutorial is expected to focus on a significant research topic and/or application of multimedia information processing and retrieval.

Proposals should be submitted in single PDF file by email to Tutorial Chairs via [], and must include the following information:

* Title of the Tutorial
* Names, titles, affiliations, and primary contact email of the Tutorial Organizers/Speakers
* Preference for 1.5 hour or 3h event
* 300-word Abstract (for publicity purposes)
* Full description of the Tutorial including topics covered by the Tutorial and a brief description and detail of each topic
* CV’s for Organizers/Speakers including relevant publications and list of tutorials given in past conferences or workshops (if any)
* Planned materials to be distributed to attendees (if any)

Each proposal will be evaluated by Tutorial Chairs based on their estimated benefit to the community. Specific factors to be considered include relevance, timeliness, importance, experience, and the Organizers’/Speakers’ qualifications.

IEEE MIPR 2021 local arrangements will provide for rooms and necessary equipment needed for the tutorial session (microphones, video projector, and screen). Each tutorial speaker will need to cover her/his registration.

**Important Dates**

* Proposal deadline: November 6, 2020
* Notification of acceptance: November 13, 2020
* Camera-ready (1-page abstract of the Tutorial) deadline: January 8, 2021

*Call for Workshop Proposals*

IEEE MIPR 2021 invites proposals for half- or full-day workshops to be held during the conference. Workshops are expected to focus on new research directions and novel applications of multimedia information processing and retrieval.

Workshop proposals should be submitted in plain text or PDF, by e-mail to Workshop Chairs via [], and must include the following elements:

* Title and its acronym
* Duration (full-day or half-day)
* Description of the workshop topic
* A draft CFP (not exceeding 500 words)
* Short description of how the organizers plan to attract quality submissions
* Preliminary list of invited speakers (if any)
* Information on past editions (if any)
* Short biographies of the organizers
* Contact information of the organizers (including names, affiliations, mailing addresses, and e-mail addresses)

After a workshop proposal is accepted, the organizers should create a Web page for the workshop and notify the workshop chairs of its URL. The main conference web site will provide a link to each workshop.

**Important Dates**

* Workshop proposal deadline: September 4, 2020
* Workshop proposal notification: September 11, 2020
* Paper submission deadline: November 6, 2020
* Notification of acceptance: December 25, 2020
* Camera-ready deadline: January 8, 2021

*Call for Special Session Proposals*

IEEE MIPR 2021 will take place in Tokyo, Japan on March 22-24, 2021 []. The conference will provide a forum for original research contributions and practical system design, implementation, and applications of multimedia information processing and retrieval. At this time, we invite you to propose special sessions for MIPR 2021. Special sessions supplement the regular program for MIPR 2021. They provide new and emerging topics in the fields of multimedia information processing and retrieval. Each special session should provide an overview of the state-of-the-art and highlight important research directions in a field of special interest to MIPR participants. Each Special Session should be a focused effort rather than defined broadly.

Each special session should consist of about 5 oral papers with authors from at least three independent institutions. The session organizers will be responsible for the selection of these papers. Special session papers can be invited or submitted. They will supplement the regular research papers and be included in the proceedings of MIPR 2021.

* Title of the special session
* Session abstract (approximately 100 words), with stating the importance of the topic and the rationale for the session
* Names and affiliations of the organizers (including brief bios and contact information)
* List of potential authors committed to submit paper (including a tentative title and a 300-word abstract for each paper)

Once the proposal has been approved, it is the duty of the organizers to publicize their special session among researchers and practitioners in each session field. The organizers will organize the review process as below.

1. Establish an independent program committee for your Special Session (SS-PC).
2. Assign 3 reviewers through SS-PC to each submitted paper.
3. Arrange a draft of peer-reviewed result for each paper, and suggest it to the program co-chairs and special session co-chairs (the final judgment is achieved by program co-chairs).

If a proposal is not accepted, potential papers in that proposal can still be submitted to regular track. If a significant number of the papers are rejected after peer-review for an approved Special Session, this Special Session may be cancelled or merged to other sessions.

Those who are interested in organizing a special session should submit a proposal with the above requirements by email to the Special Session co-chairs [], and all the papers in the special sessions should follow the same style as the regular MIPR 2021 papers.

**Important Dates**

* Proposal deadline: September 4, 2020
* Proposal notification: September 11, 2020
* Paper deadline: November 6, 2020
* Notification: December 25, 2020
* Camera-ready deadline: January 8, 2021

*Conference Organizing Committee*

Honorary Co-Chairs:
Hiroyuki Kitagawa, University of Tsukuba, Japan
Kiyoharu Aizawa, The University of Tokyo, Japan
Shin'ichi Satoh, National Institute of Informatics, Japan
Shu-Ching Chen, Florida International University, USA

General Co-Chairs:
Benoit Huet, Median Technologies, France
Jianquan Liu, NEC Corporation, Japan
Keiji Yanai, The University of Electro-Communications, Japan

Program Co-Chairs:
Naoko Nitta, Osaka University, Japan
Shuqiang Jiang, Chinese Academy of Sciences, China
Toshihiko Yamasaki, The University of Tokyo, Japan
Vincent Oria, New Jersey Institute of Technology, USA

Special Session Co-Chairs:
Kyoung-Sook Kim, National Institute of Advanced Industrial Science and Technology, Japan
Lin Li, Wuhan University of Technology, China
Tomoko Kajiyama, Hiroshima City University, Japan

Workshop Co-Chairs:
Jiaying Liu, Peking University, China
Masakazu Iwamura, Osaka Prefecture University, Japan
Pradeep K. Atrey, University at Albany, SUNY, USA

Tutorial Co-Chairs:
Chengcui Zhang, The University of Alabama at Birmingham, USA
Go Irie, NTT, Japan
Roger Zimmermann, National University of Singapore, Singapore
Zheng Wang, National Institute of Informatics, Japan

Demo Co-Chairs:
Hideki Nakayama, The University of Tokyo, Japan
Qiang Ma, Kyoto University, Japan
Ramazan Savas Aygun, Kennesaw State University, USA

Poster Co-Chairs:
Terumi Umematsu, NEC Corporation, Japan
Yoko Yamakata, The University of Tokyo, Japan

Award Committee Co-Chairs:
Homer Chen, National Taiwan University, Taiwan
Mei-Ling Shyu, University of Miami, USA
Mohan Kankanhalli, National University of Singapore, Singapore

Sponsorship & Industry Co-Chairs:
Atsushi Keyaki, Denso IT Labs, Japan
Guan-Ming Su, Dolby Labs, USA
Min Luo, EY Advanced Technology Tax Lab, Japan
Yoji Kiyota, LIFULL Co., Ltd., Japan
Yongqing Sun, NTT, Japan
Yusuke Uchida, Mobility Technologies Co., Ltd., Japan

Publicity Co-Chairs:
Abdulmotaleb El Saddik, University of Ottawa, Canada
Balakrishnan Prabhakaran, University of Texas at Dallas, USA
Cathal Gurrin, Dublin City University, Irland
Chong-Wah Ngo, City University of Hong Kong, Hong Kong
Hisashi Miyamori, Kyoto Sangyo University, Japan
Ichiro Ide, Nagoya University, Japan
Kien A. Hua, University of Central Florida, USA
Ling Guan, Ryerson University, Canada
Makoto Onizuka, Osaka University, Japan
Min Chen, University of Washington Bothell, USA
Toshiyuki Amagasa, University of Tsukuba, Japan
Wen-Huang Cheng, National Chiao Tung University, Taiwan

Local Arrangement Co-Chairs:
Xueting Wang, The University of Tokyo, Japan
Yusuke Matsui, The University of Tokyo, Japan

Publication Co-Chairs:
Atsushi Hashimoto, OMRON SINIC X Corporation, Japan
Masato Shirai, Shimane University, Japan

Finance Co-Chairs:
Shigeyuki Sakazawa, Osaka Institute of Technology, Japan
Wei-Bang Chen, Virginia State University, USA

Registration Co-Chairs:
Nakamasa Inoue, Tokyo Institute of Technology, Japan
Yuyang Dong, NEC Corporation, Japan

Web & SNS Co-Chairs:
Takahiro Komamizu (Web), Nagoya University, Japan
Yuanyuan Wang (SNS), Yamaguchi University, Japan


If you have any questions, please try to contact us by the following mailing list.


3-3-18(2021-09-08) The 3rd IEEE Workshop on Fake Multimedia (FakeMM'21), Tokyo, Japan

The  3rd IEEE Workshop onFake Multimedia (FakeMM'21)

September 8-10, 2021

Tokyo, Japan


Identification of fake content, be it text, image, audio or video, is a hot topic since the rise of modern

web and social media. This is because a vast amount of information, some of which could be fake,

gets created and shared on these platforms. A wider dissemination of fake information via social

media, news sites, and blogs can cause a significant swing to one’s mindset. Although there has

been a significant progress in multimedia security and forensics research, the modern web and

social media avenues for creation and sharing of multimedia content poses fresh challenges related

to fake content identification.

This is the third edition of the FakeMM workshop (after the first successful FakeMM’18 in Miami and

FakeMM'19 in San Jose) and it aims to bring forward further advances in the area of fake multimedia

in terms of its proactive identification and the prevention of spread of such content. We invite latest

and high-quality papers presenting or addressing issues related to fake multimedia, but not limited to:

  • Fake email detection and prevention.

  • Fake news detection.

  • Fake content detection over social media.

  • Content management policy for news publishers.

  • Content filtering for web.

  • Impact and severity of fake content.

  • Secure models, policies and practices for safe content filtering.

  • Identification and credibility of the author and the publishing source of fake content.

  • Fake content alert mechanisms.

  • Impact of AI on fake content generation.

Important Dates

Paper submission deadline:

15 March 2021

Paper acceptance notification:

31 March 2021

Paper Submission

Full-length papers of 6 pages in length reporting on original research are solicited.

The reviewing is double blind and author’s submission are available on:


Organizing Co-chairs

Pradeep K. Atrey, State University of New York, Albany, USA. [Contact person:]

Manoranjan Mohanty, University of Technology, Sydney, Australia

Priyadarsi Nanda, University of Technology, Sydney, Australia

Siwei Lyu, University at Buffalo, State University of New York, USA


3-3-19(2021-09-27) 23rd International Conference on Speech and Computer (SPECOM-2021), St Petersburg, Russia





23rd International Conference on Speech and Computer (SPECOM-2021)

September 27-30, 2021, St. Petersburg, Russia




Due to the COVID pandemic in the world, SPECOM-2021 conference with satellite events may be partially or fully organized as a teleconference via Zoom service within the announced dates. In the case of a teleconference, essentially reduced registration fees are provided for authors, as well as a free registration for participants. The proceedings will be prepared in time and published by Springer in LNCS/LNAI book series, the on-line proceedings will be available before the conference start.



June 14, 2021 .......... Submission of full papers (final date)

July 14, 2021 ........... Notification of acceptance/rejection

July 25, 2021 ........... Camera-ready papers

July 30, 2021 ........... Early registration



Prof. Junichi YAMAGISHI, National Institute of Informatics (NII), Tokyo, Japan – Automatic detection of generated voices and faces – ASVspoof and deepfake detection.




The conference is organized by the St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS, St. Petersburg, Russia) in cooperation with the Moscow State Linguistic University (MSLU, Moscow, Russia).



SPECOM attracts researchers, linguists and engineers working in the following areas of speech science, speech technology, natural language processing, human-computer interaction:

Affective computing

Audio-visual speech processing

Corpus linguistics

Computational paralinguistics

Deep learning for audio processing

Feature extraction

Forensic speech investigations

Human-machine interaction

Language identification

Multichannel signal processing

Multimedia processing

Multimodal analysis and synthesis

Sign language processing

Speaker recognition

Speech and language resources

Speech analytics and audio mining

Speech and voice disorders

Speech-based applications

Speech driving systems in robotics

Speech enhancement

Speech perception

Speech recognition and understanding

Speech synthesis

Speech translation systems

Spoken dialogue systems

Spoken language processing

Text mining and sentiment analysis

Virtual and augmented reality

Voice assistants



6th International Conference on Interactive Collaborative Robotics ICR-2021:



The official language of the event is English. However, papers on processing of languages other than English are strongly encouraged.



The conference program will include presentation of invited talks, oral presentations, and poster/demonstration sessions.



Authors are invited to submit full papers of 8-12 pages formatted in the Springer LNCS style. Each paper will be reviewed by at least three independent reviewers (single-blind), and accepted papers will be presented either orally or as posters. Papers submitted to SPECOM must not be under review by any other conference or publication during the SPECOM review cycle, and must not be previously published or accepted for publication elsewhere. The authors are asked to submit their papers using the on-line submission system:



SPECOM Proceedings will be published by Springer as a book in the Lecture Notes in Artificial Intelligence (LNAI/LNCS) series listed in all major international citation databases.



Alexey KARPOV - SPIIRAS, SPC RAS, St. Petersburg, Russia

Rodmonga POTAPOVA - MSLU, Moscow, Russia



All correspondence regarding the conference should be addressed to SPECOM-2021 Secretariat




3-3-20(2021-09-30) Call for proposals 2023 IEEE Int.Wkshp on Machine Learning and Signal Processing (MLSP)

Call for Proposals

2023 IEEE International Workshop on
Machine Learning for Signal Processing (MLSP)


IEEE Signal Processing Society?s Machine Learning for Signal Processing Technical Committee (MLSP TC) is soliciting proposals from researchers interested in organizing the 2023 MLSP Workshop. The MLSP Workshop is a four-day workshop and will include tutorials on the first day.
Proposals will be reviewed by the MLSP TC and proposal finalists will be invited to present (virtually) at the TC meeting during MLSP 2021 that will be held between October 25-28.

Proposing teams are asked to create a proposal that follows the following outline:

  1. Location and Venue: Give an idea on the venue size and facilities.
  2. Conference Dates: Ensure they do not conflict with major holidays, or other SPS conferences and workshops. Typically, the workshop is held during the period of mid-September to mid-October.
  3. Organizing Committee Members: Build the organizing committee considering factors including (a) active SPS members; (b) diversity in geographical, industry and academia, age, and gender; (c) conference and/or workshop experience; (d) event management experience. For examples, refer to, or
  4. Technical Program: Consider the overall structure and conference model; innovative initiatives; student and young professional initiatives; and industry-participation/support initiatives.
  5. Budget including registration fees.
  6. Hotels in the area that cater to different attendee budget levels.
  7. Travel and transportation between the nearest airport and the conference venue.
  8. Any other relevant information about the venue or the organization.

Important Dates:

  • Intention letter deadline: September 15, 2021
  • Deadline for submission of proposals: September 30, 2021
The intention letter deadline is September 15, 2021, and the deadline for submission of proposals is September 30, 2021. Please submit your proposal to the MLSP TC Chair, Zheng-Hua Tan, at, and the MLSP Workshop Sub-Committee Chair, Murat Akcakaya,, via email. We encourage you to contact them with questions or to obtain further details about the content of the proposals.

3-3-21(2021-10-06) ESANN 2021 - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium

ESANN 2021 - 29th European Symposium on Artificial Neural Networks,

Computational Intelligence and Machine Learning

Bruges, Belgium, 6-7-8 October 2021


2nd Call for papers


The call for papers is available at  Deadline for submissions: May 10, 2021.


The ESANN conferences cover machine learning, artificial neural networks, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered.  In addition to regular sessions, 7 special sessions will be organized on the following topics:

- Anomaly and change point detection in geometric and non vector data

- Complex Data: Learning Trustworthily, Automatically, and with Guarantees

- Federated Learning – Methods, Applications and Beyond

- Deep learning for graphs

- Interpretable Models in Machine Learning and Explainable Artificial Intelligence

- Machine Learning for Measuring and Analyzing Online Social Communications

- Machine learning and data mining for urban mobility intelligence


ESANN 2021 builds upon a successful series of conferences organized each year since 1993. ESANN has become a major scientific event in the machine learning, computational intelligence and artificial neural networks fields over the years.


The conference will be organized in Bruges, one of the most beautiful medieval towns in Europe. Designated as the 'Venice of the North', the city has preserved all the charms of the medieval heritage. Its centre, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum.  We hope that October 2021 will be the right time to organize a physical conference again, after the Covid-19 pandemic; current forecasts are optimistic for events organized after the summer 2021.  Of course health and safety of the participants are our top priority; in the unfortunate event that the situation is not safe yet, the conference will be organized online on the same dates.


We hope to receive your submission to ESANN 2021 and to see you in Bruges!


3-3-22(2021-10-18) ACM ICMI 2021: Call for Doctoral Consortium, Montreal, Canada

Doctoral Consortium - Call for Contributions

ACM ICMI 2021: Call for Doctoral Consortium
18-22 Oct 2021, Montreal, Canada

The goal of the ACM ICMI Doctoral Consortium (DC) 
is to provide PhD students with an opportunity to present their work to a 
group of mentors and peers from a diverse set of academic and industrial institutions, 
to receive feedback on their doctoral research plan and progress, 
and to build a cohort of young researchers interested in designing 
and developing multimodal interfaces and interaction. 
We invite students from all PhD granting institutions who are in the 
process of forming or carrying out a plan for their PhD research in the area
of designing and developing multimodal interfaces. We expect to provide economic support to most attendees 
that will cover part of their costs (travel, registration, meals etc.).

Who should apply?
While we encourage applications from students at any stage of doctoral training, 
the doctoral consortium will benefit most the students who are in the process of 
forming or developing their doctoral research. These students will have passed their qualifiers or 
have completed the majority of their coursework, will be planning or developing their dissertation research, 
and will not be very close to completing their dissertation research. Students from any PhD granting 
institution whose research falls within designing and developing multimodal interfaces and interaction are encouraged to apply.

Why should you attend?
The DC provides an opportunity to build a social network that includes the cohort of DC students, 
senior students, recent graduates, and senior mentors. Not only is this an opportunity to get feedback 
on research directions, it is also an opportunity to learn more about the process and to understand what comes next. 
We aim to connect you with a mentor who will give specific feedback on your research and whom you can talk to during lunch. 
We specifically aim to create an informal setting where students feel supported in their professional development.

    09:00 - 09:30: Invited talk
    09:30 - 11:00: DC talks 1
    11:00 - 11:30: Coffee break
    11:30 - 13:00: DC talks 2
    13:00 - 14:30: Lunch mentoring session
    14:30 - 15:15: Panel discussion (senior PhD students and recent graduates)
    15:15 - 15:45: Coffee break
    15:45 - 17:00: Table discussions (small group discussions about topics of interest)

Submission Guidelines:
Graduate students pursuing a PhD degree in a field related to designing multimodal interfaces should submit the following materials:
    1. Extended Abstract: A four-page description of your PhD research plan and progress in the ACM SigConf format. 
       Your extended abstract should follow the same outline, details, and format of the ICMI short papers. 
       The submissions will not be anonymous. In particular, it should cover:
        - The key research questions and motivation of your research;
        - Background and related work that informs your research;
        - A statement of hypotheses or a description of the scope of the technical problem;
        - Your research plan, outlining stages of system development or series of studies;
        - The research approach and methodology;
        - Your results to date (if any) and a description of remaining work;
        - A statement of research contributions to date (if any) and expected contributions of your PhD work;
    2. Advisor Letter: A one-page letter of nomination from the student's PhD advisor. This letter is not a letter of support. 
       Instead, it should focus on the student's PhD plan and how the Doctoral 
       Consortium event might contribute to the student's PhD training and research.
    3. CV: A two-page curriculum vitae of the student.

All materials should be prepared in PDF format and submitted through the ICMI submission system. 

Review Process:
The Doctoral Consortium will follow a review process in which submissions will be evaluated  
by a number of factors including 
(1) the quality of the submission, 
(2) the expected benefits of the consortium for the student's PhD research, and 
(3) the student's contribution to the diversity of topics, backgrounds, and institutions, in order of importance. 

More particularly, the quality of the submission will be evaluated based on the potential contributions 
of the research to the field of multimodal interfaces and its impact on the field and beyond. 
Finally, we hope to achieve a diversity of research topics, disciplinary backgrounds, 
methodological approaches, and home institutions in this year's Doctoral Consortium cohort. 
We do not expect more than two students to be invited from each institution to represent a diverse sample. 
Women and other underrepresented groups are especially encouraged to apply.

Financial Support:
The conference is pleased to offer partial financial support for doctoral students participating 
in the Doctoral Consortium and attending the conference. Only students who apply and are accepted 
for participation in the Doctoral Consortium can be considered for financial support. 
The number and size of the offers of financial support are contingent upon the number of invited student participants.

All authors of accepted submissions are expected to attend the Doctoral Consortium 
and the main conference poster session. The attendees will present their PhD work 
as a short talk at the Consortium and as a poster at the conference poster session. 
A detailed program for the Consortium and the participation guidelines for the poster 
session will be available after the camera-ready deadline.

    - Submission format: Four-page extended abstract using the ACM format (
    - Submission system:
    - Selection process: Peer-Reviewed
    - Presentation format: Talk on consortium day and participation in the conference poster session
    - Proceedings: Included in conference proceedings and ACM Digital Library
    - Doctoral Consortium Co-chairs: 
        a) Iolanda Leite (KTH Royal Institute of Technology) and 
        b) Alessandro Vinciarelli (University of Glasgow).

Submission: July 2nd Notification: Camera ready: August 16th 

Important Dates:
Submission deadline         July 2nd, 2021
Notifications August 6th, 2021
Camera-ready August 16th, 2021 

For more information and updates on the ICMI 2021 Doctoral Consortium, 
visit the Doctoral Consortium page of the main conference website (
For further questions, contact the Doctoral Consortium co-chairs:
    - Iolanda Leite (
    - Alessandro Vinciarelli (

3-3-23(2021-10-18) Call for ICMI 2021 Long and Short Papers (updated)

Call for ICMI 2021 Long and Short Papers

ICMI 2021: Call for Long and Short Papers
18-22 Oct 2021, Montreal, Canada

Call for Long, Short and Blue Sky Papers

The 23rd International Conference on Multimodal Interaction (ICMI 2021) will be held in Montreal, Canada. 
ICMI is the premier international forum for multidisciplinary research on multimodal human-human 
and human-computer interaction, interfaces, and system development. 
The conference focuses on theoretical and empirical foundations, component technologies, 
and combined multimodal processing techniques that define the field of multimodal interaction analysis, 
interface design, and system development.

We are keen to showcase novel input and output modalities and interactions to the ICMI community. 
ICMI 2021 will feature a single-track main conference which includes: keynote speakers, 
technical full and short papers (including oral and poster presentations), 
Blue Sky papers, demonstrations, exhibits, doctoral spotlight papers, and late-breaking papers. 

The conference will also feature workshops and grand challenges. 
The proceedings of ICMI 2021 will be published by ACM as part of their series
of International Conference Proceedings and Digital Library, 
and the adjunct proceedings will feature the workshop papers

We also want to welcome conference papers from behavioral and social sciences. 
These papers allow us to understand how technology can be used to increase our 
scientific knowledge and may focus less on presenting technical or algorithmic novelty. 
For this reason, the 'novelty' criteria used during ICMI 2021 review will be based on 
two sub-criteria (i.e., scientific novelty and technical novelty as described below). 
Accepted papers at ICMI 2021 only need to be novel on one of these sub-criteria. 
In other words, a paper which is strong on scientific knowledge contribution 
but low on algorithmic novelty should be ranked similarly to a paper 
that is high on algorithmic novelty but low on knowledge discovery.

- Scientific Novelty: Papers should bring some new knowledge to the scientific community. 
  For example, discovering new behavioral markers that are predictive of mental health 
  or how new behavioral patterns relate to children's interactions during learning. 
  It is the responsibility of the authors to perform a proper literature review and clearly 
  discuss the novelty in the scientific discoveries made in their paper.

- Technical Novelty: Papers reviewed with this sub-criterion should include novelty in their computational 
  approach for recognizing, generating or modeling data. Examples include: novelty in the learning 
  and prediction algorithms, in the neural architecture, or in the data representation. 
  Novelty can also be associated with new usages of an existing approach.

This year's conference theme: In the past years and specially 2020, the questions of Behavioral Health 
and Virtual Connectivity have become central to our life. 
In particular, COVID-19 has disrupted our normal social life and interactions at work, 
bringing challenges but also opportunities to improve our team sociability and productivity. 
This situation calls for multimodal systems to enhance social and emotional remote interaction 
as well as to increase productivity during remote collaboration. 
Our behavioral health has been severely impacted the past months. 
The needs for non-intrusive sensing technology, smart environments (e.g., elderly home monitoring), 
wearable and assistive devices for rehabilitation, well-being and ageing population 
and multimodal interfaces to support behavioral changes have become a crucial necessity. 
As such, this year, ICMI welcomes contributions on our theme for Behavioral Health and Virtual Connectivity.

Additional topics of interest include but are not limited to:

- Affective computing and interaction
- Cognitive modeling and multimodal interaction
- Gesture, touch and haptics
- Healthcare, assistive technologies
- Human communication dynamics
- Human-robot/agent multimodal interaction
- Interaction with smart environment
- Machine learning for multimodal interaction
- Mobile multimodal systems
- Multimodal behavior generation
- Multimodal datasets and validation
- Multimodal dialogue modeling
- Multimodal fusion and representation
- Multimodal interactive applications
- Speech behaviors in social interaction
- System components and multimodal platforms
- Visual behaviours in social interaction
- Virtual/augmented reality and multimodal interaction

Blue Sky Papers

ICMI 2021 is pleased to partner with the Computing Community Consortium (CCC) to initiate 
a new Blue Sky paper track that emphasizes innovative, visionary, and high-impact contributions. 
This track solicits papers relevant to ICMI content that go beyond the usual research paper 
to present new visions that stimulate the ICMI community to pursue innovative new directions. 
They may challenge existing assumptions and methodologies,or propose new applications or theories. 
The papers are encouraged to present high-risk controversial ideas. Submitted papers are expected 
to represent deep reflection, to argue rigorously, and to present ideas from 
a high-level synthetic viewpoint (e.g., multidisciplinary, based on multiple methodologies). 
Submissions should be 4 pages, independent of references. The CCC will further distribute 
and publicize any papers published in this track, and they will sponsor awards 
to honor the first ($1,000), second ($750), and third ($500) place papers, in the form of travel grants. 
The submission deadline is the same with main conference papers.

Updated ICMI'21 timeline:
June 2 (Extended)       Final paper submission deadline
June 3-5  SPCs bidding period
June 5-10       Reviewer assignment period
July 7         Review completion deadline
July 7-12      Rebuttal period
July 13-18    Reviewer discussion
July 21        Meta-review deadline
July 26     Authors' notification
Camera-ready paper: August 16, 2021
Presenting at main conference: October 18-22, 2021

3-3-24(2021-10-18) Call for Multimodal Grand Challenges @ ICMI2021, Montreal, Canada
Call for Multimodal Grand Challenges
ICMI 2021: Call for Multimodal Grand Challenges
18-22 Oct 2021, Montreal, Canada

We are calling for teams to propose one or more ICMI Multimodal Grand Challenges.

The International Conference on Multimodal Interaction (ICMI) is the premier international forum 
for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, 
and system development. 
Developing systems that can robustly understand human-human 
communication or respond to human input requires identifying the best algorithms and their failure modes.
 In fields such as computer vision, speech recognition, computational (para-) linguistics and physiological 
signal processing, for example, the availability of datasets and common tasks have led to great progress.
We invite the ICMI community to collectively define and tackle the scientific Grand Challenges in our domain for the next 5 years.
ICMI Multimodal Grand Challenges aim to inspire new ideas in the ICMI community and create momentum for future collaborative work. 
Analysis, synthesis, and interactive tasks are all possible.

Challenge papers will be indexed in the main proceedings of ICMI.

We invite organizers from various fields related to multimodal interaction to propose and run Grand Challenge events. 
We are looking for exciting and stimulating challenges including but not limited to the following categories:

- Dataset-driven challenge: This challenge will provide a dataset that is exemplary of the complexities 
of current and future multimodal problems, and one or more multimodal 
tasks whose performance can be objectively measured and compared in rigorous conditions. 
Participants in the Challenge will evaluate their methods against the challenge data in order to identify areas of strengths and weaknesses.
- Use-case challenge: This challenge will provide an interactive problem system (e.g. dialog-based or non-verbal-based) 
  and the associated resources, which can allow people to participate through the integration 
  of specific modules or alternative full systems. Proposers should also establish systematic evaluation procedures.
- Health challenge: This challenge will provide a dataset that is exemplary 
  of a health related task, whose analysis, diagnosis, treatment or prevention can be aided by Multimodal 
  Interactions. The challenge should focus on exploring the benefits of multimodal (audio, visual, physiological, etc) solutions for the stated task.
- Policy challenge: Legal, ethical, and privacy issues of Multimodal Interaction systems in the age of AI. 
  The challenge could revolve around opinion papers, panels, discussions, etc.

Prospective organizers should submit a five-page maximum proposal containing the following information:

2.Abstract appropriate for possible Web promotion of the Challenge
3.Distinctive topics to be addressed and specific goals
4.Detailed description of the Challenge and its relevance to multimodal interaction
5.Length (full day or half day)
6.Plan for soliciting participation
7.Description of how submissions (challenge?s submissions and papers) will be evaluated, and a list of proposed reviewers
8.Proposed schedule for releasing datasets (if applicable) and/or systems (if applicable) and receiving submissions
9.Short biography of the organizers (preferably from multiple institutions)
10.Funding source (if any) that supports or could support the challenge organization
11.Draft call for papers; affiliations and email address of the organisers; 
        summary of the Grand Challenge; 
        list of potential Technical Program Committee members 
        and their affiliations, important dates

Proposals will be evaluated based on originality, ambition, feasibility, and implementation plan. 
A Challenge with dataset(s) or system(s) that has had pilot results to ensure 
its representativity and suitability to the proposed task will be given preference for acceptance; 
an additional 1 page description must be attached in such case. 
Continuation of or variants on the 2019 challenges are welcome, 
though we ask for submissions of this form to highlight the number 
of participants that attended during the previous year and describe 
what changes (if any) will be made from the previous year.

The ICMI organizers will offer support with basic logistics, 
which includes rooms and equipment to run the Workshop, 
coffee breaks can be offered if synchronised with the main conference.

Important Dates and Contact Details

Proposals due: January 27, 2021
Proposal notification: February 3, 2021
Paper camera-ready: August 17, 2021
Grand challenge date: October 18 or 22, 2021

Proposals should be emailed to both ICMI 2021 Multimodal Grand Challenge Chairs, 
Jean-Marc Odobez and Dirk Heylen via 
Prospective organizers are also encouraged to contact the co-chairs if they have any questions. 
Proposals are due by January 27, 2021. Notifications will be sent on February 3, 2021.

You can unsubscribe for this list at any time through this link:

Delete | Reply | Reply to All | Forward | Redirect | View Thread | Blacklist | Whitelist | Message Source | Save as | Print
Move | Copy

3-3-25(2021-10-18) Cf Workshops International Conference on Multimodal Interaction (ICMI 2021), Montreal, Canada

ICMI 2021: Call for Workshops

The International Conference on Multimodal Interaction (ICMI 2021)
will be held in in Montreal, Canada, October 18-22nd, 2021. ICMI is
the premier international conference for multidisciplinary research on
multimodal human-human and human-computer interaction analysis,
interface design, and system development. ICMI has developed a
tradition of hosting workshops in conjunction with the main conference
to foster discourse on new research, technologies, social science
models and applications. Examples of recent workshops include:

- Media Analytics for Societal Trends
- Neuromanagement and Intelligent Computing
- Multi-sensorial Approaches to Human-Food Interaction
- Multimodal e-Coaches
- Group Interaction Frontiers in Technology
- Modeling Cognitive Processes from Multimodal Data
- Human-Habitat for Health
- Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction
- Investigating Social Interactions with Artificial Agents
- Child Computer Interaction
- Insights on Group & Team Dynamics
- Multimodal Interaction for Education

We are seeking workshop proposals on emerging research areas related
to the main conference topics, and those that focus on
multi-disciplinary research. We would also strongly encourage
workshops that will include a diverse set of keynote speakers (factors
to consider include: gender, ethnic background, institutions, years of
experience, geography, etc.).

The content of accepted workshops are under the control of the
workshop organizers. Workshops may be of a half-day or one day in
duration. Workshop organizers will be expected to manage the workshop
content, solicit submissions, be present to moderate the discussion
and panels, invite experts in the domain, conduct the reviewing
process, and maintain a website for the workshop. Workshop papers will
be indexed by ACM Digital Library in an adjunct proceedings, and a
short workshop summary by the organizers will be published in the main
conference proceedings.


Prospective workshop organizers are invited to submit proposals in PDF
format (Max. 3 pages). Please email proposals to the workshop chairs:
Akane Sano and Emily Mower Provost (
The proposal should include the following:

- Workshop title
- List of organizers including affiliation, email address, and short biographies
- Workshop motivation, expected outcomes and impact
- Tentative list of keynote speakers
- Workshop format (by invitation only, call for papers, etc.),
anticipated number of talks/posters, workshop duration (half-day or
full-day) including tentative program
- Planned advertisement means, website hosting, and estimated participation
- Paper review procedure (single/double-blind, internal/external,
solicited/invited-only, pool of reviewers, etc.)
- Paper submission and acceptance deadlines
- Special space and equipment requests, if any

Important Dates:
Workshop proposal submission: Monday, February 8, 2021
Notification of acceptance: Monday, February 22, 2021
Workshop papers due: End of July, 2021 (suggested)
Workshop Date: October 18-22, 2021


3-3-26(2021-10-20) ACM Multimedia, Chengdu, China

===== ACM Multimedia 2021 =====

Oct. 20-24, Chengdu
More details please visit:

1. Call for Papers

ACM Multimedia is the premier international conference in multimedia. It covers multiple emerging fields focusing on advancing the research and applications of many media, including but not limited to images, text, audio, speech, music, sensor and social data.  It strongly encourages a complete and integrated approach to exchange, process and utilize information across modalities, as well as all cutting-edge research on each medium with potential of great positive impacts on everyday lives and technological breakthroughs.
While the community has a tradition of developing and innovating AI and system approaches to handle big data and improve users? experiences on engaging and interacting with multimedia, it is also uniquely angled towards novel applications and urgent industrial challenges. As such the conference openly embraces new intellectual perspectives from both industry and academia, and welcomes submissions from related fields, such as artificial intelligence, vision and languages, data sciences, HCI and multimedia signal processing, as well as healthcare, education and beyond.  We invite the submissions in four major themes of multimedia.

Engaging Users with Multimedia
        Emotional and social signals
        Multimedia search and recommendations
        Summarization, analysis and storytelling

        Interactions and quality of experiences
        Art and culture
        Multimedia applications

Multimedia Systems
        Systems and middleware
        Transport and delivery
        Data systems management and indexing

Understanding Multimedia Content
        Multimodal fusion and embedding
        Vision and language
        Media interpretation

2. Highlights of ACM Multimedia 2020

Scientific Diversity: It is among our top priorities to ensure a top-quality conference that covers a full diversity of all fields of multimedia research including a variety of media modalities by addressing both technological and practical challenges.

Value: We strive to select the most innovative and the highest-quality research aiming at the most impactful novelty on individual media and/or from a systematic perspective of innovating and integrating multiple components across modalities.

Sharing: We value the sharing of not only knowledge (in the form of papers, presentations and demos) but also the code and open-source software. While we will continue the implementation of the ACM Artifact Review and Badging, best efforts will be made on sharing and preserving the open-source code and systems resulting from the published papers.

3. Location

The conference will be held in Chengdu, the capital city of the Sichuan Province in China.

4. Important Dates

Reproducibility Companion Paper - 7 Feb 2021

Workshop Proposals Submission - 20 Feb 2021

Grand Challenge Proposal Submission - 10 Jan 2021

Grand Challenge Proposal Notification - 31 Jan 2021

Regular Papers Submission - 3 Apr 2021 (Abstract: 27 Mar 2021)

Open Source Competition Submission - 7 Jun 2021

Brave New Ideas Submission - 31 May 2021

Interactive Artworks Submission - 15 Jun 2021

Doctorial Symposium Submission - 15 Jun 2021

Panel Proposals Submission - 15 Jun 2021

Tutorial Proposals Submission - 7 Jun 2021

Technical Demo and Video Program Submission - 15 Jun 2021

Regular Papers Notification - 3 Jul 2021

Grand Challenge Solutions Submission - 11 Jul 2021

Workshop Papers Submission - TBD

5. Organizing Committee

Honorary Chairs:

Yunhe Pan, Zhejiang University, China
Qionghai Dai, Tsinghua University, China

General Chairs:

Heng Tao Shen, University of Electronic Science and Technology of China, China
Yueting Zhuang, Zhejiang University, China
John R. Smith, IBM, USA

Technical Program Committee Chairs:

Yang Yang, University of Electronic Science and Technology of China, China
Pablo Cesar, CWI & TU Delft, Netherland
Florian Metze, Carnegie Mellon University, USA
Balakrishnan Prabhakaran, University of Texas at Dallas, USA

Panel Chairs:

Xian-Sheng Hua, Alibaba Cloud, China
Fei Wu, Zhejiang University, China
Stevan Rudinac, University of Amsterdam, The Netherlands
Xiaochun Cao, Chinese Academy of Sciences, China

Tutorials Chairs:

Changsheng Xu, Chinese Academy of Sciences, China
Dong Xu, Chinese Academy of Sciences, China
Cathal Gurrin, Dublin City University, Ireland

Workshop Chairs:

Meng Wang, Hefei University of Technology, China
Peng Wang, The University of Wollongong, Australia
Piotr Koniusz, Data61/CSIRO & Australian National University, Australia
Lianli Gao, University of Electronic Science and Technology of China, China

Brave New Idea Track Chairs:

Chang Wen Chen, University at Baffalo, USA
Zi Huang, The University of Queensland, Australia
Qin Jin, Renmin University of China, China

Multimedia Grand Challenge Chairs:

Xirong Li, Remin University, China
Lixin Duan, University of Electronic Science and Technology of China, China
Lu Fang, Tsinghua University, China
David Brady, University of Arizona, USA

Open Source Software Chairs:

Jingdong Wang, Microsoft Research Asia, China
Roger Zimmermann, National University of Singapore, Singapore
Toshihiko Yamasaki, The University of Tokyo, Japan
Qi Dai, Microsoft Research Asia, China

Technical Demo Chairs:

Jingkuan Song, University of Electronic Science and Technology of China, China
Richang Hong, Hefei University of Technology, China

Video Program Chairs:

Jitao Sang, Beijing Jiaotong University, China
Rainer Lienhart, Universität Augsburg, Germany

Interactive Arts Chairs:

Klaus Schöffmann, Klagenfurt University, Austria
Ning Xie, University of Electronic Science and Technology of China, China

Local Organization Chairs:

Yimin Zhou, University of Electronic Science and Technology of China, China
Xing Xu, University of Electronic Science and Technology of China, China

Sponsor Chairs:

Tao Mei, Jingdong, China
Qi Tian, Huawei, China

Web and Social Media Chairs:

Benoit Huet, Eurecom, France
Xiao Wu, Southwest Jiaotong University, China

Publicity Chairs:

Ann Morrison, Aalborg University, Denmark
Jinhui Tang, Nanjing University of Science and Technology, China

Finance Chairs:

Yanli Ji, University of Electronic Science and Technology of China, China
Tatsuya Harada, The University of Tokyo, Japan

History Preservation Chair:

Marcel Worring, University of Amsterdam, The Netherlands

Reproducibility Companion Chairs:

Michael Alexander Riegler, SimulaMet, Norway
Naoko Nitta, Osaka University, Japan

Doctoral Symposium Chairs:

Mohan Kankanhalli, National University of Singapore, Singapore
Bing Zeng, University of Electronic Science and Technology of China, China

Travel Grant Chairs:

Fumin Shen, University of Electronic Science and Technology of China, China
Huimin Lu, Kyushu Institute of Technology, Japan

Industry Track Chairs:

Changhu Wang, ByteDance AI Lab, China
Dong Yu, Tencent AI Lab, China
Rongrong Ji, Xiamen University, China
Jianlong Fu, Microsoft Research Asia, China
Rita Cucchiara, UNIMORE (tentative)

Proceedings Chairs:

Liqiang Nie, Shandong University, China
Hanwang Zhang, Nanyang University of Technology, Singapore
Peng Cui, Tsinghua University, China

Best Paper Committee Chair:

Tat-Seng Chua, National University of Singapore, Singapore

Registration Chairs:

Wen Li, University of Electronic Science and Technology of China, China
Yu-Gang Jiang, Fudan University, China


3-3-27(2021-10-20) 2nd International Workshop on Multimodal Conversational AI at ACM Multimedia 2021, Chengdu, China

2nd International Workshop on Multimodal Conversational AI
@ACM Multimedia 2021, October 20-24, 2021, Chengdu, China

### Deadline: July 30

The ACM Multimedia Workshop on Multimodal Conversational AI aims to bring
together researchers and practitioners in the areas of multimodal
conversational AI.
Recently, conversational systems have seen a significant rise in demand due
to modern commercial applications using systems such as Amazon's Alexa,
Apple's Siri, Microsoft's Cortana and Google Assistant. The research on
multimodal chatbots is a widely underexplored area, where users and the
conversational agent communicate by natural language and visual data.
Conversational agents are now becoming a commodity as a number of companies
push for this technology. The wide use of these conversational agents
exposes the many challenges in achieving more natural, human-like, and
engaging conversational agents. The research community is actively
addressing several of these challenges: how are visual and text data
related in user utterances? How to interpret the user intent? How to encode
multimodal dialog status? What are the ethical and legal aspects of
conversational AI?
The Multimodal Conversational AI workshop will be a forum where researchers
and practitioners share their experiences and brainstorm about success and
failures in the topic. It will also promote collaboration to strengthen the
conversational AI community at ACM Multimedia.

### Topics of Interest

- Visual conversations/dialogs
- Deep learning for multimodal conversational agents
- Preference elicitation in conversational agents
- Conversation state tracking models and online learning
- Recommendations in conversational systems
- Multimodal user intent understanding
- Opinion recommendation in conversational agents
- Supply/demand in conversational agents for e-commerce
- Reinforcement learning in conversational agents
- Resources and datasets
- Design and evaluation of conversational agents
- User-agent legal and ethical issues in conversational systems
- User-Agent experience design
- Conversational systems applications, including, but not limited to,
e-commerce, social-good, music, Web search, healthcare.

### Paper Submission Guidelines

Papers are up to 6 pages in length plus additional pages for references.
Papers will be refereed through double-blind peer review. The
proceedings will be distributed to all delegates at the conference.
All submissions must be written in English and be formatted according to
the ACM templates and guidelines. All papers should be submitted
electronically through the conference submission system.

### Timeline

- Submission: July 30
- Notification: August 26
- Camera-ready copy: September 2
- Workshop: October 20

### Organizers
- Joao Magalhaes, Universidade Nova de Lisboa, Portugal
- Alexander Hauptmann, Carnegie Mellon University, Language Technologies
- Ricardo G. Sousa, Farfetch, Portugal
- Carlos Santiago, ISR/IST, Portugal

ACM Multimedia 2022 General co-Chair 
NOVA LINCS - Laboratory for Computer Science and Informatics
Universidade NOVA de Lisboa, Portugal

3-3-28(2021-10-25) IEEE Workshop L3DAS21 Machine Learnng for 3D Audio Signal Processing, Gold Coast, Australia

IEEE MLSP Data Challenge 2021

Machine Learning for 3D Audio Signal Processing


Scope of the Challenge

The L3DAS21 Challenge for the IEEE MLSP 2021 aims at encouraging and fostering research on machine learning for 3D audio signal processing. In multi-speaker scenarios it is very important to properly understand the nature of a sound event and its position within the environment, what is the content of the sound signal and how to leverage it at best for a specific application (e.g., teleconferencing rather than assistive listening or entertainment, among others). To this end, L3DAS21 Challenge presents two tasks: 3D Speech Enhancement and 3D Sound Event Localization and Detection, both relying on first-order Ambisonics recordings in reverberant office environment.

Each task involves 2 separate tracks: 1-mic and 2-mic recordings, respectively containing sounds acquired by one Ambisonics microphone and by an array of two Ambisonics microphones. The use of two first-order Ambisonics microphones definitely represents one of the main novelties of the L3DAS21 Challenge.

  • Task 1: 3D Speech Enhancement

    The objective of this task is the enhancement of speech signals immersed in the spatial sound field of a reverberant office environment. Here the models are expected to extract the monophonic voice signal from the 3D mixture containing various background noises.The evaluation metric for this task is the sum of the short-time objective intelligibility (STOI) and word error rate (WER).

  • Task 2: 3D Sound Event Localization and Detection

    The aim of this task is to detect the temporal activities of a known set of sound event classes and, in particular, to further locate them in the space.Here the models must predict a list of the active sound events and their respective location at regular intervals of 100 milliseconds. Performance on this task is evaluated according to the location-sensitive detection error, which joins the localization and detection errors.

Besides submitting papers related to L3DAS21 Challenge, authors are encouraged to submit to this special session also papers related to the topic of machine learning for 3D audio signal processing.


  • 27 Mar 2021 ? Release of the training and development sets
  • 10 May 2021 ? Release of the evaluation test set
  • 20 May 2021 ? Deadline for submitting results for both tasks
  • 25 Oct 2021 ? Opening of the IEEE Workshop on MLSP 2021

Challenge Website and Contacts


3-3-29(2021-11-10) WMT 2021 Shared Task: Machine Translation using Terminologies, Punta Cana, Dominican Republic


WMT 2021 Shared Task: 

Machine Translation using Terminologies

November 10-11 , 2021
Punta Cana, Dominican Republic

Language domains that require very careful use of terminology are abundant. The need to adequately translate within such domains is undeniable, as shown by e.g. the different WMT shared tasks on biomedical translation.

More interestingly, as the abundance of research on domain adaptation shows, such language domains are (a) not adequately covered by existing data and models, while (b) new (or ?surge?) domains arise and models need to be adapted, often with significant downstream implications: consider the new COVID-19 domain and the large efforts for translation of critical information regarding pandemic handling and infection prevention strategies.

In the case of newly developed domains, while parallel data are hard to come by, it is fairly straightforward to create word- or phrase-level terminologies, which can be used to guide professional translators and ensure both accuracy and consistency.

This shared task will replicate such a scenario, and invites participants to explore methods to incorporate terminologies into either the training or the inference process, in order to improve both the accuracy and consistency of MT systems on a new domain.


Release of training data and terminologies    April 2021
Surprise languages announced: June 28, 2021
Test set available July 19, 2021
Submission of translations July 23, 2021
System descriptions due August 5, 2021
Camera-ready for system descriptions September 15, 2021
Conference in Punta Cana November 10-11, 2021


In this shared task, we will distinguish submissions that use the terminology only at inference time (e.g., for constrained decoding or something similar) and submissions that use the terminology at training time (e.g., for data selection, data augmentation, explicit training, etc). Note that basic linguistic tools such as taggers, parsers, or morphological analyzers are allowed in the constrained condition.

The submission report should highlight in which ways participants? methods and data differ from the standard MT approach. They should make clear which tools were used, and which training sets were used.


The shared task will focus on four language pairs, with systems evaluated:
  • English to French
  • English to Chinese
  • Two surprise language pairs English-X (announced 3 weeks before the evaluation deadline)
We will provide training/development data and terminologies for the above language pairs. Test sets will be released at the beginning of the evaluation period. The goal of this setting (with both development and surprise language pairs) is to avoid approaches that overfit on language selection, and instead evaluate the more realistic scenario of needing to tackle the new domain in a new language in a limited amount of time. The surprise language pairs will be announced 3 weeks before the start of the evaluation campaigns. At the same time we will provide training data and terminologies for the surprise language pairs.

You may participate in any or all of the language pairs.


Antonis Anastasopoulos, George Mason University
Md Mahfuz ibn Alam, George Mason University
Laurent Besacier, NAVER
James Cross, Facebook
Georgiana Dinu, AWS
Marcello Federico, AWS
Matthias Gallé, NAVER
Philipp Koehn, Facebook / Johns Hopkins University
Vassilina Nikoulina, NAVER
Kweon Woo Jung, NAVER

3-3-30(2021-11-17) PerceptiO Perception of the living , U.of Strasbourg France



Perception and the living

La perception et le vivant

University of Strasbourg, France

UR 1339 LiLPa – Linguistics, Languages and Speech Research Unit

Chair of the USIAS Language Sciences – University of Strasbourg, Institute for

Advanced Study

University of Haute-Alsace, France

UR 4363 ILLE – Research Institute for European Languages and Literatures

IdEx Symposium 2021

17-20 November

The University of Strasbourg (France), through its Linguistics, Languages and Speech Research Unit 1339 LiLPa, as well as the USIAS Chair of Language Sciences (University of Strasbourg, Institute for Advanced Study), and the University of Haute-Alsace (France), through its Institute for Research in European Languages and Literatures Re- search Unit 4363 ILLE, will host in Alsace the symposium 'PerceptiO: Perception and the living' from the 17th to the 20th of November, 2021.

Chaired by the Alsatian University duo, the international organising committee of the event will also include in its ranks (in alphabetical order of the partner countries): the Institute for Research in Language Sciences and Technologies – IRSTL of the University of Mons (Belgium), First People’s Hospital in Chengdu, First People’s Hospital in Zigong and Binzhou Medical University (China), the Modern & Classical Languages, Literatures & Cultures Department at the University of Kentucky (United States of America), Chair of French Language of the University of Opole (Poland), Assane Seck University of Ziguinchor (Senegal) and the Department of Romance Studies of Matej Bel University of Banská Bystrica, LICoLab – Language, Information and Communication Laboratory and Department of British and American Studies of the Faculty of Arts of Pavol Jozef Šafárik University in Košice (Slovakia).

  • Argument

The symposium, which will bring together specialists from all horizons (both in terms of continents and fields of specialisation), will be devoted to perception and the living, a theme that will have to be tackled under its various disci-plinary seams, whether they fall within the commonly accepted classification established since the 20th Century in the Sciences (formal, physical, life, social) or that of the Arts (architecture, sculpture, visual arts, music, literature, perform-ing arts, cinema).

The general objective of the congress will thus entail addressing the question of how (the world of) the living caters for perceptions, both in terms of apprehension, feeling, understanding, analysis, construction, of profiling, of transmis-sion as of reception, to try to uncover the still quite vague outlines of the very notion of perception and related phenom-ena, in order to further the study of known properties and/or specificities or, moreover, to shed light on novel ones. More specifically, the major tack will notably involve, from the observation of how these properties or specificities fit into the living (world), means of highlighting the duality of the ontologies of perception (sensory vs intellectual).

In practice, we shall question, starting from the living (world), in particular the matrices, the molds, the frames, the actants, the circumstances, the ins and outs of perception through, preferably, inter, trans, multi, pluri or intradisciplinary approaches – even if the mono or uni-disciplinary approach will not be excluded. Note that all types of languages, be they natural or artificial, can serve as empirical bases and that, regardless of the approach considered, experimental and/or clinical approaches will be highly appreciated, as well as contrastive ones.

To this end, whether theoretical or applied, systematic or experimental, contextual or independent, synchronic or diachronic, prescriptive, descriptive or programmatic, intra or interdisciplinary, proposals thus requested will fit into at least one pair of disciplines from the Sciences and/or the Arts, such as: mathematics-linguistics, painting-music, biol-ogy-anthropology, medicine-linguistics, anthropology-music, physics-painting, sociology-linguistics, philosophy-mathematics, psychology-anthropology, computer science-linguistics, etc.

Regarding the official classification of the High Council for the Evaluation of Research and Higher Education (HCERES) disciplinary fields, the symposium includes all disciplines: Mathematics, Physics, Earth and Universe Sci-ences, Chemistry, Engineering Sciences, Information and Communication Sciences and Technologies, Biology, Health, Agronomy, Ecology, Environment, Markets and Organisations, Standards, social institutions and behaviours, Space, environment and societies, Human spirit, language, education, Languages, Texts, Arts and cultures, Ancient and contemporary Worlds.

  • Confirmed plenary speakers (other invitations are pending)

- Professor Alain Berthoz (Collège de France, Chair of Physiology of Perception and Action)

- Professor Luc Fraisse (Institut Universitaire de France & University of Strasbourg)

- Research Director Anne Giersche (University of Strasbourg & Inserm – Cognitive neuropsychology, pathophysiol-ogy of schizophrenia)

- Professor Bernard Harmegnies (Institute for Research in Language Sciences and Technology, University of Mons)

- Professor Karine Lacombe (Sorbonne University, Inserm, Department of Infectious and Tropical Diseases, St An-toine’s Hospital, Paris)

- Professor David Poeppel (Department of Neuroscience, Max-Planck-Institute Frankfurt & New York University)

- Professor Jean-Pierre Sauvage (University of Strasbourg, Chair of Chemical Topology and Molecular Machines)

- Research Director Jean-Luc Schwartz (GIPSA-Lab, Speech-Cognition Department, Grenoble Alpes University)

  • Useful information

Proposals for papers, based on the PropCom framework below (Annex 1), will be sent simultaneously to Fabrice Marsac ( and Rudolph Sock ( before March 31st, 2021 (indicate 'Symposium Per-ceptiO 2021' as the subject).

Notifications of acceptance or rejection of proposals will be sent to the authors by 30 April 2021 at the latest, and a first provisional programme of the event will follow around 15th of May.

The D-Day, oral communications, organised around the plenary lectures, will not exceed 15 minutes (plus 5 minutes for questions). Poster sessions, which are scientifically equivalent in importance to the oral communications, will also be organised. The language of presentation will be either French or English.

After the symposium, the written contributions selected by the scientific committee will be published in 2023 as volume(s)/thematic volume(s) or varia in international journal(s).

Registration fees (150 € for permanent staff and 50 € for doctoral students) include the gala dinner on the second day (Thursday 18), the traditional paracolloquial activities (including a guided tour of the magnificent Strasbourg and its main cultural and tourist attractions, as well as the European Institutions) and the publication of contributions. Ac-commodation and other catering costs are the sole responsibility of participants.

The meeting will take place at the University of Strasbourg (Accueil – Université de Strasbourg ( and at the Maison Interuniversitaire des Sciences de l’Homme, Alsace – MISHA (Maison des Sciences de l’Homme – Alsace (MISHA)).

Depending on the sanitary context in November 2021, the symposium will be held in praesentia or will be par-tially/completely dematerialised.

  • Scientific committee

Currently being set up, the scientific committee of PerceptiO 2021 will be responsible for both the scientific review of proposals, carried out, as usual, by peers on a double-blind basis, and for reviewing subsequent submitted articles, also conducted on a double-blind basis by peers, in view of their publication in the course of 2023.

  • Organising committee

- Linguistics, Languages and Speech Research Unit UR 1339 LiLPa (University of Strasbourg, France)

- USIAS Chair of Language Sciences (University of Strasbourg, Institute for Advanced Study)

- Institute for Research in European Languages and Literatures Research Unit 4363 ILLE (University of Haute-Alsace, France)

- Institute for Research in Language Sciences and Technologies – IRSTL (University of Mons, Belgium)

- First People’s Hospital in Chengdu (China)

- First People’s Hospital in Zigong (China)

- Binzhou Medical University (China)

- Modern & Classical Languages, Literatures & Cultures Department (University of Kentucky, United States of Amer-ica)

- Chair of French language (University of Opole, Poland)

- Assane Seck University of Ziguinchor (Senegal)

- Department of Romance Studies (Matej Bel University of Banská Bystrica, Slovakia)

- LICoLab – Language, Information and Communication Laboratory & Department of British and American Studies of the Faculty of Arts (Pavol Jozef Šafárik University in Košice, Slovakia)

  • Reminder of key dates

- Submission of proposals: 31st March 2021 (deadline)

- Notification of paper acceptance or refusal: 30th April 2021 (deadline)

- Publication of the programme: around 15th of May 2021 (first provisional programme)

- Symposium: 17-20 November 2021

- Publication of accepted articles: in 2023


  • Annex n° 1: PropCom outline (2 pages maximum)

1. Title of the proposal

2. Object(s) of study, research issues

3. Objective(s), theoretical framework(s) and research hypothesis(es)

4. Methodology

5. Results

6. Five key words

7. References

8. Last name, first name and academic affiliation(s) of the author(s)

9. E-mail address(es) for correspondence

10. Specify if it is a doctoral research (if applicable, indicate the name of the thesis supervisor(s))

  • Annex n° 2: scientific committee (in the process of being set up)

The scientific committee of PerceptiO 2021 will be composed, among other members, of (teacher-)researchers from the various disciplinary fields established by the High Council for the Evaluation of Research and Higher Education (HCERES).

For the International Organising Committee,

Fabrice MARSAC et Rudolph SOCK

University of Strasbourg, France


3-3-31(2021-12-02) 2nd International Seminar on the Foundations of Speech (SEFOS II) 2021, Sonderborg, Denmark

2nd International Seminar on the Foundations of Speech (SEFOS II) 2021

Theme: Articulation and Prosody: Between Interface and Integration

Date: 2-4 December 2021, Sonderborg, Denmark


The links between articulation and prosody are a subject of growing interest. It is driven, among other things, by increasingly powerful measurement, analysis and recording techniques, by the discovery of syntagmatic and paradigmatic structures in prosody and the simultaneous undermining of strictly linear-segmental models in articulation, as well as the by rapid rise of speech technology and the associated increasing relevance of the emotions, speaking styles, attitudes, social hierarchies, social-role marking, etc. But, how far have we really come in understanding the links between articulation and prosody?


The 2nd International Seminar on the Foundations of Speech (SEFOS II) will be a forum to discuss these questions. Reflecting the development of the articulation-prosody research and continuing the successful concept of the first SEFOS, SEFOS II shall again be a strongly interdisciplinary event. We therefore cordially invite not only all members of the speech-science community to take part in SEFOS II, but also interested members from related fields such as general linguistics, medicine, audiology, psychology, rhetoric, pedagogy, language/speech technology and engineering sciences.


Due to the global COVID-19 pandemic, the organizing committee decided to conduct the conference in the form of a HYBRID CONFERENCE combining a live in person event with a virtual component.




Prof. Dr. Cécile Fougeron
Directrice de Recherche
Laboratoire de Phonétique et Phonologie
CNRS-Université Sorbonne-Nouvelle
Paris, France


Prof. Dr.-Ing. Peter Birkholz
Chair of Speech Technology and Cognitive Systems
Institute of Acoustics and Speech Communication
TU Dresden
Dresden, Germany




01 Aug 2021: Full paper submission deadline (will NOT be extended!) 
05 Sep 2021: Notification of acceptance (revised papers can be submitted until after the conference)
03 Oct 2021: Early bird registration deadline 
02-04 Dec 2021: SEFOS II conference 
27 Feb 2022:  Deadline for the resubmission of revised full papers 


NOTE THAT SEFOS II has teamed up with the proceedings branch of deGruyter, 'Sciendo', to publish widely visible (open access) article-length proceedings papers OF UP TO 15 PAGES (ABOUT 10,000 WORDS)




3-3-32(2021-12-06) 1st International Conference on Tone and Intonation (TAI) 2021

1st International Conference on Tone and Intonation (TAI) 2021

Theme: 'Tone and Intonation in a globalized, digital world'

Date: 6-9 December 2021, Sonderborg, Denmark

The 1st edition of the Tone-and-Intonation (TAI) conference series is proudly hosted by the Centre for Industrial Electronics (CIE) at the University of Southern Denmark. Being a merger of the two former conference series TAL (Tonal Aspects of Languages) and TIE (Tone and Intonation in Europe), TAI 2021 welcomes contributions on phonetic and phonological analyses of prosody including (but not limited to) topics related to the production and perception of prosody and rhythm, the semantics and pragmatics of prosody, the acquisition and teaching of prosody in L1 and L2, and cross-linguistic comparisons of prosody.
In addition, in TAI 2021 two separate special sessions will be dedicated to the challenges and opportunities that globalization and digitization hold for the speech sciences. In this context, we also encourage researchers of neighboring disciplines to submit papers related to tone and intonation to the conference.
Due to the global COVID-19 pandemic, the organizing committee decided to conduct the conference in the form of a HYBRID CONFERENCE combining a live in person event with a virtual component.
01 May 2021       Online abstract submission opens (EasyChair)
04 Jul 2021          Abstract submission deadline
05 Sep 2021        Notification of abstract acceptance
03 Oct 2021        Early bird registration deadline
6-9 Dec 2021       1st Tone-and-Intonation Conference, Sonderborg, Denmark
27 Feb *2022*    Deadline for the submission of a corrected abstract and an optional 5-page full paper (4 pages of text plus 1 page for references only)

3-3-33(2021-12-13) ASRU, Carthagena, Colombia

A S R U 2021 C a r t a g e n a

December 13rd - 17th


IEEE Automatic Speech Recognition and Understanding Workshop

The IEEE ASRU Workshop is a biennial flagship event of the IEEE Speech

and Language Processing Technical Committee.

The workshop will be held on December 13-17, 2021. Since the global

situation is still uncertain and given the slow vaccination progress

worldwide, it is likely that the workshop will be virtual. We are making

several efforts to make it in-person, but we depend on external

unpredictable factors. In any case appropriate and timely information

will be published in the website and widely distributed using all

possible ways. Even if the workshop is virtual, we hope that sometime

soon we will be able to welcome you all in Cartagena.


All papers related to automatic speech recognition and understanding

are welcome. Topics of interest include, but are not limited to:

Automatic speech recognition

ASR in adverse enviroments

New applications of ASR

Speech-to-speech translation

Spoken document retrieval

Speaker/Language recognition

Speech emotion recognition

Methods and models leveraging

multi-lingual resources

Spoken language understanding

Spoken dialog systems

Text-to-speech systems

Important dates

Paper submission opens: May. 7, 2021

Regular & Challenge paper submission (abstract): Jun 25, 2021

Regular & Challenge paper submission (final paper): Jul 2, 2021

Paper reviews returned: Aug. 18, 2021

Author response due: Aug. 25, 2021

Paper acceptance notification: Sep. 10, 2021

Author registration due: Oct. 8, 2021

Early registration due: Oct. 15, 2021

Demo submission due: Oct. 15, 2021

Demo selection notification: Oct. 29, 2021

ASRU Workshop: Dec. 13-17, 2021



Submission details

Authors are invited to prepare papers of 4-6 pages of content and

figures, plus up to 2 pages containing only references, to the ASRU

2021 website:


This is the link to download the paper submission kit:

Organizing Committee

General Chair:

Elmar Nöth

General Co-Chair:

Juan Rafael Orozco Arroyave

Technical Program Chairs:

Carlos Busso, Ville Hautamäki, Kate Knill, Helen

Meng, Michael Picheny, Bhuvana Ramabhadran,

Dayana Ribas, Korbinian Riedhammer, Isabel


Panel and Invited Speaker Chairs:

Sebastian Möller, Odette Scharenborg

Challenge, Special Session & Demonstration Chairs:

Heidi Christensen, Jesús Francisco Vargas-Bonilla,

Juan Camilo Vásquez Correa

Finance Chairs:

Sofía Aristizabal, Mauricio Correa

Publication Chair:

Tobias Bocklet

Satellite Workshop Chairs:

Carlos Ariel Ferrer, Heidi Christensen, María

Claudia González Rátiva

Publicity Chairs:

Julie Mauclair, Daniela Castaño

SLTC Liaison:

Antonio Texeira

International Liaison:

Sadaoki Furui, Hynek Hermansky, Aline


Sponsorship Chairs:

Jimmy Kunzmann, Mathew Magimai Doss, Richard


Local Arrangement Chairs:

Daniela Castaño, Mauricio Correa, Andrea





3-3-34(2021-?-?) Call for Participation: The Ninth Dialog System Technology Challenge (DSTC9)

Call for Participation: The Ninth Dialog System Technology Challenge (DSTC9)


The DSTC shared tasks have provided common testbeds for the dialog research community since 2013. From its sixth edition, it has been rebranded as 'Dialog System Technology Challenge' to cover a wider variety of dialog related problems.

 For this year's challenge, we opened the call for track proposals and selected the following four parallel tracks by peer-reviews:
 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access (Amazon Alexa AI): This track aims to allow users to have requests that are out of the scope of APIs/DB but potentially available in external knowledge sources. Track participants will develop task-oriented dialogue systems to understand relevant domain knowledge, and generate system responses with the relevant selected knowledge. In addition, the track includes evaluation on generalization over unseen domains and modalities (i.e. moving from written to spoken conversations).
 - Multi-domain Task-oriented Dialog Challenge II (Microsoft Research AI & Tsinghua University): This track follows its success in DSTC-8 continuing with the effort of building dialog systems under a multi-domain setting. This time extending the task by incorporating new datasets, creating new sub-tasks, and providing a new development platform. The new task specifically focuses on two aspects of dialog systems: language portability and end-to-end system complexity. 
- Interactive Evaluation of Dialog (CMU & USC): This track targets the creation of systems that can be effectively used in interactive settings by real users. The task is intended to move research beyond datasets, and evaluate models in interactive environments with real users allowing several valuable properties of dialog to be measured: consistency, adaptiveness and user-centric development. DialPort, a platform for interactive assessment with real users will be used for evaluation. 
- SIMMC: Situated Interactive Multi-Modal Conversational AI (Facebook Assistant & Facebook AI): This track aims to tackle grounding dialog in an evolving multi-modal contextual input. Unlike previous multimodal track challenges, where the context from the non-textual modalities (video and audio) remains unchanged as the dialog progresses, this track encompasses a rich, situated multi-modal user context in the form of a shared image or VR environment that evolves fluidly based on the dialog flow.
 Participation is welcomed from any research team (academic, corporate, non-profit, government).
 Important Dates

- Jun 15, 2020: Training data is released

- Sep 21, 2020: Test data is released

- Oct 5, 2020: Entry submission deadline
- Nov 2020: Paper submission deadline
- Spring 2021: DSTC9 workshop (venue: TBD)
 DSTC9 Organizing Committee

- Chulaka Gunasekara - IBM Research AI, USA

- Abhinav Rastogi - Google Research, USA
- Yun-Nung (Vivian) Chen - National Taiwan University, Taiwan 
- Luis Fernando D'Haro - Universidad Politécnica de Madrid, Spain
- Seokhwan Kim - Amazon Alexa AI, USA
 DSTC9 Track Organizers
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access 
- Seokhwan Kim, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Dilek Hakkani-tur (Amazon Alexa AI)
 Multi-domain Task-oriented Dialog Challenge II 
- Baolin Peng, Jianfeng Gao, Jinchao Li, Lars Liden, Minlie Huang, Qi Zhu, Runze Liang, Ryuichi Takanobu, Shahin Shayandeh, Swadheen Shukla, Zheng Zhang (Microsoft Research AI & Tsinghua University)
 Interactive Evaluation of Dialog 
- Shikib Mehri, Carla Gordon, David Traum, Maxine Eskenazi (CMU & USC)
SIMMC: Situated Interactive Multi-Modal Conversational AI 
- Ahmad Beirami, Eunjoon (EJ) Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba (Facebook Assistant & Facebook AI)
 DSTC Steering Committee

 Koichiro Yoshino - Nara Institute of Science and Technology (NAIST), Japan 
- Chiori Hori - Mitsubishi Electric Research Laboratories (MERL), USA 
- Rafael E. Banchs - Nanyang Technological University (NTU), Singapore 
- Michel Galley - Microsoft Research AI, USA
 Contact Information
 Join the DSTC mailing list to get the latest updates about DSTC9:
- To join the mailing list: visit!forum/list/join
- To post a message: send your message to
- To leave the mailing list: visit!forum/list/unsubscribe
 For specific enquiries about DSTC9: Please feel free to contact



3-3-35(2022-03-??) II Brazilian Prosody Conference, on line

 We are pleased to announce the 'II Brazilian Prosody Conference', supported by the Luso-Brazilian Association of Speech Sciences, to be held in March, 2022, totally online. The event aims to create a space for training and research on Experimental Prosody and its interfaces for students and professionals whose work involves speech, voice, singing, speech communication technologies, speech pathologies, sound production and perception, oral communication, vocal aesthetic, acoustics, language teaching and other related areas.

To better organize the conference and allow the participation of as many people as possible, we created a form that can be accessed through the links below in Portuguese, English and Spanish.
The form is simple and straightforward, so it might take less than 5 minutes to complete.
We would really appreciate it if you could get back to us till May 25th, 2021. 

Thank you very much in advance for your kind collaboration.

Organizing committee
Cristiane Conceição Silva (UFSC) - President
Leila Rechenberg (UFRGS) - Vice-president
Maryualê Malvessi Mittmann (Univali) - Secretary
André Nogueira Xavier (UFPR) - Treasurer


3-3-36(2022-06-20) 14th LREC, Marseille, France

The European Language Resources Association (ELRA) is glad to announce the 14th edition of LREC.

LREC 2022 will take place in Marseille at the Palais du Pharo (France) on June 20-25, 2022.

We hope to be able to organise a face-to-face conference, but in the unfortunate event that physical gatherings will not be yet allowed due to the Covid-19 pandemic, an online alternative will be set up.


? Main Conference: 21-22-23 June 2022

? Workshops and Tutorials: 20-24-25 June 2022


LREC is the major event on Language Resources and Evaluation for Language Technologies. LREC aims to provide an overview of the state-of-the-art, explore new R&D directions and emerging trends, exchange information regarding LRs and their applications, evaluation methodologies and tools, on-going and planned activities, industrial uses and needs, requirements coming from e-science and e-society, with respect to both scientific/technological issues as well as policy and organisational ones.

LREC provides a unique forum for researchers, industrials and funding agencies from across a wide spectrum of areas to discuss issues and opportunities, find new synergies and promote initiatives for international cooperation, in support of investigations in language sciences, progress in language technologies and development of corresponding products, services and applications, and standards.


The Scientific Programme will include invited talks, oral presentations, poster and demo presentations, and panels, in addition to a keynote address by the winner of the Antonio Zampolli Prize.

We will also organise an Industrial Track for which there will be a separate Call.


The Proceedings will include both oral and poster papers, in the same format.

There is no difference in quality between oral and poster presentations. Only the appropriateness of the type of communication (more or less interactive) to the content of the paper will be considered.


  • Nicoletta Calzolari ? CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa - Italy (Conference chair)
  • Frédéric Béchet ? LIS-CNRS, Aix Marseille University - France
  • Philippe Blache ? LPL-CNRS & Aix-Marseille University - France
  • Khalid Choukri  ? ELRA, Paris - France
  • Christopher Cieri ? Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA - USA
  • Thierry Declerck ? DFKI GmbH, Saarbrücken - Germany
  • Hitoshi Isahara ? Toyohashi University of Technology, Toyohashi - Japan
  • Bente Maegaard  ? Department of Nordic Studies and Linguistics, University of Copenhagen - Denmark
  • Joseph Mariani  ? LISN, CNRS, University Paris-Saclay, Orsay - France
  • Jan Odijk  ? UIL-OTS, Utrecht - The Netherlands
  • Stelios Piperidis ? Athena Research Center/ILSP, Athens - Greece


  • Sara Goggi ? CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa - Italy
  • Hélène Mazo ? ELDA/ELRA, Paris - France



3-3-37(2023) 13th International Conference on Multimedia Retrieval, Europe?

The ICMR Steering Committee invites interested parties to submit proposals to
host and organize the 13th International Conference on Multimedia Retrieval,
ICMR2023 (sponsored by the ACM SIGMM). ACM ICMR is the premier
scientific conference for multimedia retrieval.  Its mission is
to provide a forum to discuss,  promote and advance the
state-of-the-arts in multimedia retrieval by bringing together
researchers and practitioners in its related field. It is thus essential
to ensure that the conference includes sessions for presenting high-quality
research papers and for sharing practitioner experience.  The list of
previous ICMRs is at
We expect ICMR2023 to be held in Europe.

Parties interested in hosting ICMR2023 are invited to submit  their
proposals (20 pages or less) by Friday, 26 February 2021 by email with
the subject line: ICMR2023 to the steering committee chair.
The details of CFP is at


3-3-38New IARPA and NIST challenge:OpenASR

Dear Speech Scientist:

IARPA and NIST are pleased to announce a new speech recognition challenge: OpenASR. Registration is still open.
The goal of the OpenASR (Open Automatic Speech Recognition) evaluation is to develop methods to quickly develop speech recognition systems in a variety of genres from low-resource languages, with minimal amounts of training data. Training data for ten languages will be released to aspirants, with two evaluations conditions: constrained and unconstrained.
The OpenASR challenge was developed out of IARPA's MATERIAL program
<>, but only evaluates WER for ASR.

For more information on the OpenASR timeline and participation details,  please refer to the OpenASR webpage:

For the registration page, please visit:
Participation is open to Everyone. Feel free to spread the word to interested participants.


The OpenASR Team at IARPA and NIST


 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA