SIGDIAL 2019

11-13 September 2019, Stockholm, Sweden

Second Call for Special Sessions

http://workshops.sigdial.org/conference20

Special Session Submission Deadline: January 28, 2019

Special Session Notification: February 18, 2019

The Special Interest Group on Dialogue and Discourse (SIGDIAL) organizers welcome the submission of special session proposals. A SIGDIAL special session is the length of a regular session at the conference, and may be organized as a poster session, a panel session, a poster session with panel discussion, or an oral presentation session. Special sessions may, at the discretion of the SIGDIAL organizers, be held as parallel sessions.

The papers submitted to special sessions are handled by the special session organizers, but for the submitted papers to be in the SIGDIAL proceedings, they have to undergo the same review process as regular papers. The reviewers for the special session papers will be taken from the SIGDIAL program committee itself, taking into account the suggestions of the session organizers, and the program chairs will make acceptance decisions. In other words, special session organizers decide what appears in the session, while the program chairs decide what appears in the proceedings and the rest of the conference program.

We welcome special session proposals on any topic of interest to the discourse and dialogue communities. Topics of interest include, but are not limited to Explainable AI, Evaluation, Annotation, and End-to-end systems.

Submissions:

Those wishing to organize a special session should prepare a two-page proposal containing: a summary of the topic of the special session; a list of organizers and sponsors; a list of people who may submit and participate in the session; and a requested format (poster/panel/oral session).

These proposals should be sent to conference[at]sigdial.org by the special session proposal deadline. Special session proposals will be reviewed jointly by the general chair and program co-chairs.

Links:

Those wishing to propose a special session may want to look at some of the sessions organized at recent SIGDIAL meetings.

• http://www.sigdial.org/workshops/conference19/sessions.htm

• https://robodial.github.io/

• http://articulab.hcii.cs.cmu.edu/sigdial2016/

SIGDIAL 2019 Organizing Committee

General Chair:

Satoshi Nakamura, Nara Institute of Science and Technology, Japan

Program Chairs:

Milica Gaši

, Cambridge University, UK

Ingrid Zukerman, Monash University, Australia

Local Chair:

Gabriel Skantze, KTH, Sweden

Sponsorship Chair:

Mikio Nakano, Honda Research Institute Japan, Japan

Mentoring Chair:

Alex Papangelis, Uber AI, USA

Publication Chair:

Stefan Ultes, Daimler AG, Germany

Publicity Chair:

Koichiro Yoshino, Nara Institute of Science and Technology, Japan

SIGdial President:

Jason Williams, Apple, USA

SIGdial Vice President:

Kallirroi Georgila, University of Southern California, USA

SIGdial Secretary:

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

SIGdial Treasurer:

Ethan Selfridge, Interactions, USA

SIGdial President Emeritus:

Amanda Stent, Bloomberg, USA

Top

Welcome to INTERSPEECH 2019 ? Willkommen in Graz, Austria, Sept 15-19, 2019
http://www.interspeech2019.org

Important Dates Coming Up Soon

• Proposals due for Special Sessions and Challenges: Friday, November 30, 2018
  See Call for Special Sessions and Challenges at https://www.interspeech2019.org/calls/special_sessions_and_challenges!

• Proposals due for Satellite Workshops: to be submitted to ISCA as soon as possible!
  See Call for Satellite Workshops at https://www.interspeech2019.org/calls/satellite_events!

• Sponsoring and Exhibition opportunities: see http://www.interspeech2019.org/sponsorship_and_exhibition/letter_to_our_partners

What is new?

INTERSPEECH 2019 is the 20^th Annual Conference of the International Speech Communication Association ISCA and this anniversary edition will introduce several innovative features. These innovations will certainly contribute to raise the attractiveness of the conference beyond the high levels developed already over the past two decades:

Survey presentations have been evolved from the perspective talks at INTERSPEECH 2018 in Hyderabad. The presentations will be scheduled at the start of suitable oral presentation sessions, and will be allocated a 40-minute time slot for presentation and discussion. Presentations should aim to give an overview of the state-of-the-art for a specific topic covered by one or more of the main technical areas of the conference. The presenters will also be invited to submit survey papers to the ISCA supported journals of Computer, Speech and Language and Speech Communication. For further details, see our Call for Survey Presentations [please add link!] further below.

Childcare – the INTERSPEECH Kids: Bring your family along to Graz, Austria! Childcare will be provided free of charge for conference participants. For terms and conditions, see the conference webpage http://www.interspeech2019.org/venue_and_travel/childcare. To secure a place for your kids, we recommend to apply for this service at your earliest convenience.

Hackathons will set a stimulating atmosphere for the most creative developers in our community and beyond: through jams and challenges, we will bring together some of our brightest minds, students who are speech science and technology aficionados and who come to Graz as conference participants, as well as students who are representing the highly interdisciplinary community of several partner universities in Graz and beyond. Watch out for details to appear soon on our website http://www.interspeech2019.org or contact directly our hackathon chairs Elmar Nöth (FAU Erlangen-Nürnberg) and Johanna Pirker (TU Graz) at hackathon@interspeech2019.org.

Top

INTERSPEECH 2019

 GRAZ – AUSTRIA SEPTEMBER 15th – 19th 2019 WWW.INTERSPEECH2019.ORG

 https://interspeech2019.org

CROSSROADS OF SPEECH AND LANGUAGE 

CALL FOR PAPERS AND PROPOSALS FOR TUTORIALS, SPECIAL SESSIONS/CHALLENGES, AND SHOW & TELL

INTERSPEECH is the world‘s largest and most comprehensive conference on the science and technology of spoken language processing. INTERSPEECH conferences emphasize interdisciplinary approaches addressing all aspects of speech science and technology, ranging from basic theories to advanced applications. In addition to regular oral and poster sessions, INTERSPEECH 2019 will feature plenary talks by internationally renowned experts, tutorials, special sesssions and challenges, show & tell sessions, and exhibits. A number of satellite events will also take place around INTERSPEECH 2019.

Original papers are solicited in, but not limited to, the following areas:

1. Speech Perception, Production and Acquisition

2. Phonetics, Phonology, and Prosody

3. Analysis of Paralinguistics in Speech and Language

4. Speaker and Language Identification

5. Analysis of Speech and Audio Signals

6. Speech Coding and Enhancement

7. Speech Synthesis and Spoken Language Generation

8. Speech Recognition – Signal Processing, Acoustic Modeling, Robustness, an Adaptation

9. Speech Recognition – Architecture, Search, and Linguistic Components

10. Speech Recognition – Technologies and Systems for New Applications

11. Dialog Systems and Analysis of Conversation

12.Spoken Language Processing – Translation, Information Retrieval, Summarization,

   Resources, and Evaluation

 A complete list of the scientific areas and topics including special sessions is available at » www.interspeech2019.org

 PAPER SUBMISSION

Papers intended for INTERSPEECH 2019 should be up to four pages of text. An optional fifth page could be used for references only. Paper submissions must conform to the format defined in the paper preparation guidelines and as detailed in the author’s kit on the conference webpage. Please be aware that INTERSPEECH 2019 will use new templates and submissions will be accepted only in the new format. Submissions may also be accompanied by additional files such as multimedia files, to be included on the proceedings’ USB drive. Authors must declare that their contributions are original and have not been submitted elsewhere for publication. Papers must be submitted via the online paper submission system. The working language of the conference is English, and papers must be written in English.

We look forward to receiving your submissions and to your participation in INTERSPEECH 2019.

 IMPORTANT DATES

 » November 30, 2018 Special session/challenges proposals due

 » February 1, 2019 Tutorial proposals due

 » February 15, 2019 Submission portal opens

 » February 28, 2019 Satellite workshops/events proposals due

 » March 29, 2019 Paper submission deadline

 » April 5, 2019 Final paper submission deadline

 » April 26, 2019 Show & Tell proposals due

 » June 17, 2019 Acceptance/rejection notification

 » June 24, 2019 Registration opens

 » July 1, 2019 Camera-ready paper due

 General Chairs:

 Gernot Kubin, TU Graz, Austria

 Zdravko Kacˇicˇ, University of Maribor, Slovenia

Technical Chairs:

 Thomas Hain, U Sheffield, UK

 Björn Schuller, U Augsburg/Imperial College, Germany/UK

Organising Committee Members:

  Michiel Bacchiani, Google NY, USA

 Gerhard Backfried, Sail Labs Vienna, Austria

 Jamilla Balint, TU Graz, Austria

 Eugen Brenner, TU Graz, Austria

 Mariapaola D‘Imperio, Aix Marseille U, France

 Dina ElZarka, U Graz, Austria

 Tim Fingscheidt, TU Braunschweig, Germany

 Anouschka Foltz, U Graz, Austria

 Anna Fuchs, AVL Graz, Austria

 Panayiotis Georgiou, USC Los Angeles, USA

 Franz Graf, Joanneum Research Graz, Austria

 Markus Gugatschka, MU Graz, Austria

 Martin Hagmüller, TU Graz, Austria

 Petra Hödl, U Graz, Austria

 Robert Höldrich, KU Graz, Austria

 Mario Huemer, JKU Linz, Austria

 Dorothea Kolossa, RU Bochum, Germany

 Christina Leitner, Joanneum Research Graz, Austria

 Stefanie Lindstaedt, KNOW Centre Graz, Austria

 Helen Meng, CU Hong Kong, China

 Florian Metze, CMU Pittsburgh, USA

 Pejman Mowlaee, Widex/TU Graz, Denmark/Austria

 Elmar Noeth, FAU Erlangen-Nürnberg, Germany

 Franz Pernkopf, TU Graz, Austria

Ingrid Pfandl-Buchegger, U Graz, Austria

 Lukas Pfeifenberger, Ognios Salzburg, Austria

 Johanna Pirker, TU Graz, Austria

Christoph Prinz, Sail Labs Vienna, Austria

 Michael Pucher, ÖAW Vienna, Austria

 Philipp Salletmayr, Nuance Vienna, Austria

 Barbara Schuppler, TU Graz, Austria

 Dagmar Schuller, audEERING, Germany

Jessica Siddins, U Graz, Austria 

Wolfgang Wokurek, U Stuttgart, Germany

 Kai Yu, Shanghai Jiao Tong University, China

Top

INTERSPEECH 2019: Call for Satellite Workshops

The Organizing Committee of INTERSPEECH 2019 is now inviting proposals for satellite workshops, to be held in proximity to the main conference.

Proposals should be submitted as soon as possible to the ISCA workshop portal (https://www.isca-speech.org/iscaproposals/workshop.php) since every satellite workshop needs ISCA endorsement!

The Organizing Committee will work to facilitate the organization of such satellite workshops, to stimulate discussion in research areas related to speech and language, at locations in Europe, and around the same time as INTERSPEECH 2019. We are particularly looking forward to proposals from neighboring countries. If you are interested in organizing a satellite workshop, or would like a planned event to be listed as an official satellite event, please contact the Satellite Workshop Chairs at workshops@interspeech2019.org. See http://interspeech2019.org/calls/satellite_events for further details.

As possible sites for your satellite events may we propose the following cities within easy reach from the conference location (either by train, bus, or rental car):

• Graz, Austria, the INTERSPEECH 2019 host city, with several supporting institutions;

• Maribor, Slovenia, just 50 km away, where we provide local support via the University of Maribor;

• Vienna, Austria, just 200 km away, where we provide local support via the Austrian Academy of Sciences.

Important Dates

• Submission to ISCA workshop portal: As soon as possible since every satellite workshop needs ISCA endorsement!

• Once ISCA endorsement has been granted, requests for co-registration with INTERSPEECH2019 have to be submitted by February 28, 2019.

• Confirmation as an INTERSPEECH2019 satellite event by March 15, 2019.

If you have any questions about whether a potential event would be a good candidate for an INTERSPEECH 2019 satellite workshop feel free to contact the Satellite Workshop Chairs at workshops@interspeech2019.org.

Sincerely

Jessica Siddins (U Graz)
Zdravko Kačič (U Maribor)
Michael Pucher (ÖAW Vienna)

Satellite Workshop Chairs for INTERSPEECH 2019

Top

INTERSPEECH 2019: Call for Special Sessions & Challenges

Important Dates

Proposal submission deadline: Friday, November 30, 2018
Notification of pre-selection: Tuesday, January 1, 2019
Final list of special sessions: Monday, June 17, 2019

Special Sessions & Challenges

Submissions of Special Sessions & Challenges proposals are encouraged for INTERSPEECH 2019, covering interdisciplinary topics and/or important new emerging areas of interest related to the main conference topics. Submissions related to the special focus of the conference, Crossroads of Speech and Language(http://www.interspeech2019.org/about/conference_theme), are particularly welcome. Apart from supporting a particular theme, special sessions may also have a format that is different from a regular session.

Each special session proposal must contain the following information.

• The title of the proposed special session.

• The names and affiliations of the organizers, including contact information and a brief biography for each organizer.

• Up to five bullet points explaining what factors make the proposed session special.

• A summary (up to one page) stating the importance of the session’s topic and objectives. Furthermore, the session format should be clearly defined. The summary should also explain why the topic cannot be properly covered by regular conference sessions.

• A tentative list of researchers who could contribute papers to the session. Note that with a nominal 50% acceptance rate for Interspeech papers, this means that special sessions should have a minimum of 12 anticipated submissions, unless their format allocates time to something other than paper presentations.

• Additional or non-standard resources (e.g., data, equipment, poster stands, etc.) required for organizing the special session.

Proposals will be evaluated by the organizing committee for relevance and significance. Papers for approved Special Sessions have to be submitted following the same schedule and procedure as regular papers; the papers will undergo the same review process by anonymous and independent reviewers. Special session organizers will be involved in the reviewer assignment and in the final decisions.

Special session proposers are invited to submit a proposal via email to the Special Session Chairs Tim Fingscheidt (TU Braunschweig), Mariapaola d’Imperio (Aix-Marseille U), and Franz Pernkopf (TU Graz) at special_sessions@interspeech2019.org no later than Friday, November 30, 2018. Please do not hesitate to ask before submitting your proposal if something is not fully clear to you. Notification of pre-selection is scheduled for Tuesday, January 1, 2019. Final acceptance will take place shortly after paper decisions are completed, depending on the number of accepted papers submitted to each special session.

Top

NEW! INTERSPEECH 2019: Call for Survey Presentations NEW!

Important Dates

Proposal submission deadline: Friday May 3, 2019
Notification of selection: Monday, June 17, 2019

Survey Presentations

Interspeech is the annual flagship conference of the International Speech Communication Association (ISCA), which brings together a truly interdisciplinary group of experts from academia and industry to present and discuss the latest research, technology advances and scientific discoveries in a five-day event. As such Interspeech constantly innovates and adapts. Beyond plenary talks, oral and poster presentations recent years have seen new ideas on how to engage with experts and industry.

The 20th edition of Interspeech conferences, to take place in Graz, Austria, will introduce a range of new presentation formats. Given the complexity of speech communication science and technology the need for detailed technical review of sub-areas of research has become more critical than ever.

We invite proposals for innovative and engaging Research Survey Presentations. The talks are aimed to be scheduled at the start of suitable oral presentation sessions, and will be allocated a 40-minute time slot for presentation and discussion. Presentations should aim to give an overview of the state of the art for a specific topic covered by one or more of the main technical areas of Interspeech 2019, namely

1. Speech Perception, Production and Acquisition

2. Phonetics, Phonology, and Prosody

3. Analysis of Paralinguistics in Speech and Language

4. Speaker and Language Identification

5. Analysis of Speech and Audio Signals

6. Speech Coding and Enhancement

7. Speech Synthesis and Spoken Language Generation

8. Speech Recognition — Signal Processing, Acoustic Modeling, Robustness, Adaptation

9. Speech Recognition — Architecture, Search, and Linguistic Components

10. Speech Recognition — Technologies and Systems for New Applications

11. Spoken Dialog Systems and Analysis of Conversation

12. Spoken Language Processing — Translation, Information Retrieval, Summarization, Resources and Evaluation

Proposals for Survey Presentations are required to include

• The presenter’s name, title, and short bio (100 words), and (if applicable) a list of co-contributors.

• Title, an outline and a description of the proposed talk (max 500 words). The description should include statements on the relevance of the talk, and the potential target audience.

• A current CV of the presenter including a list of publications

Proposals will be evaluated by the technical programme and organising committees for relevance and significance, taking balance across areas and the available presentation slots into account (maximum 10 presentations). The presenters of the Interspeech 2019 survey talks will be invited to submit survey papers to the ISCA supported journals of Computer, Speech and Language and Speech Communication with the aim to be included in a Special Issue on the State of the Art in Speech Science and Technology.

Survey presentation proposers are invited to submit a proposal via email to the Technical Program Chairs: tpc-chairs@interspeech2019.org no later than Friday May 3, 2019. Please do not hesitate to contact the technical chairs for any questions that may arise prior to proposal submission.  Notification of selection is scheduled for June 17, 2019.

Thomas Hain and Björn Schuller

INTERSPEECH 2019 Technical Program Chairs

Top

Call for Tutorials at INTERSPEECH 2019

INTERSPEECH conferences are attended by researchers with a long-term track-record in speech sciences and technology, as well as by early-stage researchers or researchers interested in a new domain within the INTERSPEECH areas. An important part of the conference are the tutorials to be held on the first day of the conference, September 15, 2019. Presented by speakers with long and deep expertise in speech, they will provide their audience with a rich learning experience and an exposure to longstanding research problems, contemporary topics of research as well as emerging areas.

We encourage proposals for addressing fundamental or advanced topics in an introductory style as well as for targeting experienced researchers who want to dig deeper into a given new topic.

Tutorials, each of three-hour duration, shall introduce an emerging area of speech-related research, or present an overview of an established area of research, rather than focus on the presenter’s individual research.

Date and Venue of the Tutorials

September 15, 2019; two 3h sessions, in the morning and in the afternoon, in the main conference location (Messecongress Graz).

Proposals Should Include (in this Order)

Tutorial title

Presenter(s) (name and affiliation)

Contact information (email, telephone)

3-4 sentence abstract summarizing the proposed tutorial that could be used as an advertisement

Description of the proposal (1-2 pages description plus a few relevant references and any webpages/material useful for reviewing the proposal)

Explanation of relevance of the proposed tutorial (0.5 – 1 page)

Tutorial logistics, including

• Duration (1 session = 3 hours = 2 x 90 minutes plus refreshment break)

• Description of presentation format (e.g., one or more presenters etc.)

• Equipment required for the tutorial

• Preference for type of accompanying material (handouts, storage devices with media, etc.)

Presenter information

• Biography of presenter(s)

• Key publications of presenter(s) on the tutorial topic

• List of previous tutorial experience

Audience information

• Target audience (e.g., new researchers to the field, research students, specialists of adjacent fields, etc.)

• Other considerations/ comments

• Bibliography (from description)

Submission Procedure

Proposals for INTERSPEECH 2019 tutorials may be no more than 4 pages long and must conform to the format stated above; please use clear headings to indicate each point. Proposals should be submitted by email to tutorials@interspeech2019.orgby February 1, 2019 and notification of accepted proposals will be given by March 1, 2019.

By submitting a proposal, the presenter(s) understand the ISCA policy of strongly encouraging video-recording of the tutorials for education purposes if the proposal is accepted. Access to recording materials will be given via ISCA Video Archives.

To access the online call for tutorials, visit http://interspeech2019.org/calls/tutorials.

Questions? Please Contact: tutorials@interspeech2019.org

The tutorial chairs:

Barbara Schuppler, Graz University of Technology

Florian Metze, Carnegie Mellon University, Pittsburgh

Dorothea Kolossa, Ruhr University Bochum

Top

INTERSPEECH 2021
Brno, Czech Republic, August 30 - September 3, 2021
Chairs : Hynek Hermansky and Honza Cernocky 
22^nd INTERSPEECH event

Top

 Tenth Christian Benoît Award conferred by the International Speech Communication Association  and the Association Francophone de la Communication Parlée
  Deadline May 15, 2019
 
The Christian Benoît Award has been conferred periodically by the Association Christian Benoit until 2017. In 2018, the oversight of this Award was assumed  by ISCA and sponsored jointly by both ISCA and AFCP. It is awarded through a competitive nomination and review process to promising young scientists in the domain of SPEECH COMMUNICATION to further their career in the field. The focus of the award’s research topic may emphasize basic science or applied research projects.
 
The Award provides the elected scientist with financial support for the development of a personal short-term research project that:  (1) illustrates concretely the achievements of her/his research work; (2) could help in promoting his/her work in the scientific community, institutions and grant agencies in their geographical region/country; (3) gives an overall view of the state of the art in the particular research domain.  The proposed research project can take on the form of a demonstration, a technical product/system, or of a pedagogical multi-media product (movie, website, interactive software…).
 
The Award is valued at 7,500 Euros(*)
 
The commitments of the elected scientist who receives the award are: -- to attend the Interspeech-2019 Conference in Graz, Austria -- to deliver the final product of the project within 2 years -- to present her/his results at a future ISCA-endorsed event, specific to the research domain of the applicant.
 
In the application, the candidate should provide -- a statement of research interests (2 pages max), -- a detailed curriculum vitae including a list of the most relevant publications for the project. -- a description of the proposed short-term research project (5 to 15 pages max). The description should include a presentation of the scientific and/or pedagogical objectives and the methodological aspects, a link to the former research work of the applicant, and a detailed description of the provisional budget.
 
Applications will be evaluated by an international committee including experts in the field of Speech Communication and representatives of the institutions supporting the award.
 
Applications should be sent to gerard.bailly@gipsa-lab.fr before Monday May 15, 2019 Electronic submissions are mandatory
 
The successful candidate will be notified by June 15, 2019. The Award will be conferred at the Interspeech-2019 Conference in Graz, Austria (www.interspeech2019.org)
 
-------------------------------------------------------------------------------------------

* 3,500 Euros will be given immediately; with the remaining 4,000 Euros  available on reception of the multimedia project by the chair of the ISCA Award committee. Travel and registration costs necessary to attend the Interspeech 2019 Conference will have to be paid from this grant.
** For details about the Association Christian Benoît and the past awardees of the Christian Benoît Award see http://www.gipsa-lab.fr/acb/

Top

FIRST CALL FOR PAPERS

SIGDIAL 2019 CONFERENCE

September 11-13, 2019

http://www.sigdial.org/workshops/conference20/

The 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2019) will be held on September 11-13, 2019 at the KTH Royal Institute of Technology in Stockholm, Sweden.

SIGDIAL will be temporally co-located with Interspeech 2019, which will be held on September 15-19 in Graz, Austria (https://www.interspeech2019.org). 

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 nineteen 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.

Keynote Speakers:  Dan Bohus, Mirella Lapata, Helen Meng

TOPICS OF INTEREST

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

• Applications of Dialogue and Discourse Processing Technology

SPECIAL SESSIONS

SIGDIAL 2019 will include two special sessions (TBA).

Please see the individual special session pages (TBA) for additional information and submission details. In order for papers submitted to special sessions to appear in the SIGDIAL conference proceedings, they must undergo the regular SIGDIAL review process.

SUBMISSIONS

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 poster presentation. Accepted short papers will be presented as posters.

• Long papers must be no longer than eight 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 papers should be no longer than four 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
Papers that have been or will be submitted to other meetings or publications must provide this information (see submission link). SIGDIAL 2019 cannot accept work for publication or presentation that will be (or has been) published elsewhere. Any questions regarding submissions can be sent to program-chairs[at]sigdial.org.

Blind Review
Building on previous year’s move to anonymous long and short paper submissions, SIGDIAL 2019 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.

Submission Link and Deadlines
Authors have to fill in the submission form in the START system and upload a pdf of their paper before the May 19 deadline. Updates of a final pdf file will be permitted until May 19, 23:59 GMT.

https://www.softconf.com/j/sigdial2019/

IMPORTANT NOTE: ADOPTION OF ACL AUTHOR GUIDELINES 

As noted above, SIGDIAL 2019 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.

MENTORING

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.

BEST PAPER AWARDS

In order to recognize significant advancements in dialogue/discourse science and technology, SIGDIAL 2019 will include 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.

IMPORTANT DATES

• Long, Short & Demonstration PDF Submission: 19 May 2019 (23:59, GMT)

• Long, Short & Demonstration Paper Notification: 28 June 2019

• Final Paper Submission: 21 July 2019 (23:59, GMT)

• Conference: 11-13 September, 2019

SIGDIAL 2019 ORGANIZING COMMITTEE

General Chair:

Satoshi Nakamura, Nara Institute of Technology, Japan

Program Chairs:

Ingrid Zukerman, Monash University, Australia

Milica Gasic, Saarland University, Germany

Local Chair:

Gabriel Skantze, KTH Royal Institute of Technology, Sweden

Sponsorship Chair:

Mikio Nakano, Honda Research Institute Japan, Japan

Mentoring Chair:

Alexandros Papangelis, Uber AI, USA

Publication Chair

Stefan Ultes, Daimler AG, Germany

Publicity Chair:

Koichiro Yoshino, Nara Institute of Science and Technology, Japan

SIGdial President:

Jason Williams, Apple, USA

SIGdial Vice President:

Kallirroi Georgila, University of Southern California, USA

SIGdial Secretary:

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

SIGdial Treasurer:

Ethan Selfridge, Interactions, USA

SIGdial President Emeritus:

Amanda Stent, Bloomberg, USA

Top

SIGDIAL 2019

11?13 September 2019, Stockholm, Sweden

Call for Special Sessions

http://workshops.sigdial.org/conference20

Special Session Submission Deadline: January 28, 2019 Special Session Notification: February 18, 2019

The Special Interest Group on Discourse and Dialogue (SIGDIAL) organizers welcome the submission of special session proposals.

A SIGDIAL special session is the length of a regular session at the conference, and may be organized as a poster session, a panel session, a poster session with panel discussion, or an oral presentation session.

Special sessions may, at the discretion of the SIGDIAL organizers, be held as parallel sessions.

The papers submitted to special sessions are handled by the special session organizers, but for the submitted papers to be in the SIGDIAL proceedings, they have to undergo the same review process as regular papers. The reviewers for the special session papers will be taken from the SIGDIAL program committee itself, taking into account the suggestions of the session organizers, and the program chairs will make acceptance decisions. In other words, special session organizers decide what appears in the session, while the program chairs decide what  appears in the proceedings and the rest of the conference program.

We welcome special session proposals on any topic of interest to the discourse and dialogue communities. Topics of interest include, but are not limited to Explainable AI, Evaluation, Annotation, and End?to?end systems.

Submissions:

Those wishing to organize a special session should prepare a two-page proposal containing: a summary of the topic of the special session; a list of organizers and sponsors; a list of people who may submit and participate in the session; and a requested format (poster/panel/oral  session).

These proposals should be sent to conference[at]sigdial.org by the special session proposal deadline. Special session proposals will be reviewed jointly by the general chair and program co?chairs.

Links:

Those wishing to propose a special session may want to look at some of the sessions organized at recent SIGDIAL meetings.

http://www.sigdial.org/workshops/conference19/sessions.htm

https://robodial.github.io/

http://articulab.hcii.cs.cmu.edu/sigdial2016/

SIGDIAL 2019 Organizing Committee

General Chair:

Satoshi Nakamura, Nara Institute of Science and Technology, Japan

Program Chairs:

Milica Ga?i?, Cambridge University, UK

Ingrid Zukerman, Monash University, Australia

Local Chair:

Gabriel Skantze, KTH, Sweden

Sponsorship Chair:

Mikio Nakano, Honda Research Institute Japan, Japan

Mentoring Chair:

Alex Papangelis, Uber AI, USA

Publication Chair:

Stefan Ultes, Daimler AG, Germany

Publicity Chair:

Koichiro Yoshino, Nara Institute of Science and Technology, Japan

SIGdial President:

Jason Williams, Apple, USA

SIGdial Vice President:

Kallirroi Georgila, University of Southern California, USA

SIGdial Secretary:

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

SIGdial Treasurer:

Ethan Selfridge, Interactions, USA

SIGdial President Emeritus:

Amanda Stent, Bloomberg, USA

Top

HSCR19 - The 3rd International Workshop on the HISTORY OF SPEECH COMMUNICATION RESEARCH

13-14 September, 2019 in Vienna, Austria

<https://hscr19.kfs.oeaw.ac.at>

CALL FOR PAPERS

The aim of this workshop is to bring together researchers that are interested in historical aspects of all areas of speech communication research (SCR) with a focus on the interdisciplinary nature of the different fields of research.

A special interest of the 2019 workshop is on the relation between science and technology that can be exemplified through the history of SCR ? including methods from the 20th century that are no longer the state-of-the-art but of historical relevance. Interesting questions in this respect are: How can knowledge transfers between science and technology be exemplified by the history of SCR? What is the relation between SCR and artistic practices? How was speech communication research influenced by the medical sciences?

Like the past HSCR workshops that were held in 2015 in Dresden and 2017 in Helsinki this workshop is a satellite event of the INTERSPEECH conference which will be held in Graz, Austria <https://www.interspeech2019.org/>, a meeting that advertises with the Austro-Hungarian speech communication pioneer Wolfgang von Kempelen.

Invited speaker is Peter Donhauser from the Institute for Media Archeology in Vienna.

Important Dates:

Full paper submission: May 24, 2019

Notification of acceptance: July 1, 2019

Camera-ready paper submission: July 19, 2019

Workshop: September 13-14, 2019

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

Workshop organisation:

Michael Pucher, Acoustics Research Institute, Vienna, Austria

Juergen Trouvain, Saarland University, Saarbruecken, Germany

Carina Lozo, Acoustics Research Institute, Vienna, Austria

Top

CALL FOR PAPERS:

30th Conference on Electronic Speech Signal Processing (ESSV) 2019

Venue: TU Dresden, Germany

Web: www.essv.de/essv2019

ORGANIZERS:

Peter Birkholz, Simon Stone (TU Dresden, Germany)

CONFERENCE TOPICS:

* Speech recognition and natural language understanding
* Speech synthesis and natural language generation
* Measuring, processing, and modeling articulation
* Phonetic, syntactic, semantic, and pragmatic aspects in technical applications
* Multimodal dialog systems
* Models of speech acquisition
* Acoustic and visual pattern recognition
* Musical, biological, and technical signals ? applications and processing
* Applications in medical, healthcare, and rehabilitation technologies
* Cognitive and neural systems
* Speech technology in industrial and home environments

KEYNOTE SPEAKERS:

* Ercan Altinsoy
* Sidney Fels
* Christian Herbst
* Jose Gonzalez
* Korin Richmond

IMPORTANT DATES:

* Conference: March 6 - 8, 2019
* Submission deadline for extended abstract (1 page): November 30, 2018
* Notification of acceptance: until December 14, 2018
* Camera-ready paper submission deadline: January 25, 2019

CONFERENCE LANGUAGES:

German and English

Top

13th INTERNATIONAL CONFERENCE ON LANGUAGE AND AUTOMATA THEORY AND APPLICATIONS
 
LATA 2019
 
Saint Petersburg, Russia
 
March 25-29, 2019
 
Organized by:
           
Saint Petersburg State University
and
Institute for Research Development, Training and Advice, Brussels/London
 
http://lata2019.irdta.eu/
*************************************************************************
 
AIMS:
 
LATA is a conference series on theoretical computer science and its applications. LATA 2019 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from classical theory fields as well as application areas.
 
VENUE:
 
LATA 2019 will take place in Saint Petersburg, whose historic centre is a UNESCO World Heritage Site. The conference site shall be the historical Twelve Collegia building (https://en.wikipedia.org/wiki/Twelve_Collegia), built in ca. 1740,
which was used for the Russian government in the 18th century, and which
has been the main building of Saint Petersburg State University since 1835.
 
SCOPE:
 
Topics of either theoretical or applied interest include, but are not limited to:
 
algebraic language theory
algorithms for semi-structured data mining
algorithms on automata and words
automata and logic
automata for system analysis and programme verification
automata networks
automatic structures
codes
combinatorics on words
computational complexity
concurrency and Petri nets
data and image compression
descriptional complexity
foundations of finite state technology
foundations of XML
grammars (Chomsky hierarchy, contextual, unification, categorial, etc.)
grammatical inference and algorithmic learning
graphs and graph transformation
language varieties and semigroups
language-based cryptography
mathematical and logical foundations of programming methodologies
parallel and regulated rewriting
parsing
patterns
power series
string processing algorithms
symbolic dynamics
term rewriting
transducers
trees, tree languages and tree automata
weighted automata
 
STRUCTURE:
 
LATA 2019 will consist of:
 
invited talks
peer-reviewed contributions
 
INVITED SPEAKERS:
 
Henning Fernau (University of Trier), Modern Aspects of Complexity within Formal Languages
 
Pawe? Gawrychowski (University of Wroc?aw), tba
 
Edward A. Lee (University of California, Berkeley), Observation, Interaction, Determinism, and Free Will
 
Vadim Lozin (University of Warwick), From Words to Graphs, and Back
 
Esko Ukkonen (University of Helsinki), Pattern Discovery in Biological Sequences
 
PROGRAMME COMMITTEE:
 
Krishnendu Chatterjee (Institute of Science and Technology Austria, AT)
Bruno Courcelle (University of Bordeaux, FR)
Manfred Droste (University of Leipzig, DE)
Travis Gagie (Diego Portales University, CL)
Peter Habermehl (Paris Diderot University, FR)
Tero Harju (University of Turku, FI)
Markus Holzer (University of Giessen, DE)
Radu Iosif (Verimag, FR)
Kazuo Iwama (Kyoto University, JP)
Juhani Karhumäki (University of Turku, FI)
Lila Kari (University of Waterloo, CA)
Juha Kärkkäinen (University of Helsinki, FI)
Bakhadyr Khoussainov (University of Auckland, NZ)
Sergey Kitaev (University of Strathclyde, UK)
Shmuel Tomi Klein (Bar-Ilan University, IL)
Olga Kouchnarenko (University of Franche-Comté, FR)
Thierry Lecroq (University of Rouen, FR)
Markus Lohrey (University of Siegen, DE)
Sebastian Maneth (University of Bremen, DE)
Carlos Martín-Vide (Rovira i Virgili University, ES, chair)
Giancarlo Mauri (University of Milano-Bicocca, IT)
Filippo Mignosi (University of L'Aquila, IT)
Victor Mitrana (Polytechnic University of Madrid, ES)
Joachim Niehren (INRIA Lille, FR)
Alexander Okhotin (Saint Petersburg State University, RU)
Dominique Perrin (University of Paris-Est, FR)
Matteo Pradella (Polytechnic University of Milan, IT)
Jean-François Raskin (Université Libre de Bruxelles, BE)
Marco Roveri (Bruno Kessler Foundation, IT)
Karen Rudie (Queen's University, CA)
Wojciech Rytter (University of Warsaw, PL)
Kai Salomaa (Queen's University, CA)
Sven Schewe (University of Liverpool, UK)
Helmut Seidl (Technical University of Munich, DE)
Ayumi Shinohara (Tohoku University, JP)
Hans Ulrich Simon (Ruhr-University of Bochum, DE)
William F. Smyth (McMaster University, CA)
Frank Stephan (National University of Singapore, SG)
Martin Sulzmann (Karlsruhe University of Applied Sciences, DE)
Jorma Tarhio (Aalto University, FI)
Stefano Tonetta (Bruno Kessler Foundation, IT)
Rob van Glabbeek (Data61, CSIRO, AU)
Margus Veanes (Microsoft Research, US)
Mahesh Viswanathan (University of Illinois, Urbana-Champaign, US)
Mikhail Volkov (Ural Federal University, RU)
Fang Yu (National Chengchi University, TW)
Hans Zantema (Eindhoven University of Technology, NL)
 
ORGANIZING COMMITTEE:
 
Alexander Okhotin (Saint Petersburg, co-chair)
Manuel Parra-Royón (Granada)
Dana Shapira (Ariel)
David Silva (London, co-chair)
 
SUBMISSIONS:
 
Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (all included) and should be prepared according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). If necessary, exceptionally authors are allowed to provide missing proofs in a clearly marked appendix.
 
Submissions have to be uploaded to:
 
https://easychair.org/conferences/?conf=lata2019
 
PUBLICATIONS:
 
A volume of proceedings published by Springer in the LNCS series will be available by the time of the conference.
 
A special issue of a major journal will be later published containing peer-reviewed substantially extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation.
 
REGISTRATION:
 
The registration form can be found at:
 
http://lata2019.irdta.eu/Registration.php
 
DEADLINES (all at 23:59 CET):
 
Paper submission: November 18, 2018
Notification of paper acceptance or rejection: December 16, 2018
Final version of the paper for the LNCS proceedings: December 23, 2018
Early registration: December 23, 2018
Late registration: March 11, 2019
Submission to the journal special issue: June 29, 2019
 
QUESTIONS AND FURTHER INFORMATION:
 
david (at) irdta.eu

Top

The Second (2019) IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR'19)

http://www.ieee-mipr.org
San Jose, CA, USA
March 28-30, 2019

New forms of multimedia data (such as text, numbers, tags, networking, signals,
geo-tagged information, graphs/relationships, 3D/VR/AR and sensor data, etc.)
has emerged in many applications in addition to traditional multimedia data
(image, video, audio). Multimedia has become the biggest of big data as
the foundation of today's data-driven discoveries. Almost all disciplines of
science and engineering, as well as social sciences, involve multimedia data
in some forms, such as recording experiments, driverless cars, unmanned aerial
vehicles, smart communities, biomedical instruments, security surveillance.
Some recent events demonstrate the power of real-time broadcast of unfolding
events on social networks. Multimedia data is not just big in volume, but also
multi-modal and mostly unstructured. Storing, indexing, searching, integrating,
and recognizing from the vast amounts of data create unprecedented challenges.
Even though significant progress has been made processing multimedia data,
today's solutions are inadequate in handling data from millions of sources
simultaneously.

The IEEE International Conference on Multimedia Information
Processing and Retrieval (IEEE-MIPR) aims to provide a forum for original research
contributions and practical system design, implementation, and applications
of multimedia information processing and retrieval for single modality or
multiple modalities. The target audiences will be university researchers,
scientists, industry practitioners, software engineers, and graduate students
who need to become acquainted with technologies for big data analytics, machine
intelligence, information fusion in multimedia information processing and retrieval.
A collection of keynotes, open panels, and workshops will be held, together
with paper/poster sessions.

The conference will accept regular papers (6 pages), short papers (4 pages),
and demo papers (2 pages). Authors are encouraged to compare their approaches,
qualitatively or quantitatively, with existing work and explain the strength
and weakness of the new approaches. Selected submissions will be invited to submit
to journal special issues.

The conference includes (but not limited) the following topics of multimedia
data processing and retrieval.

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

Systems and Infrastructures
  * Multimedia Systems and Middleware
  * Telepresence and Virtual/Augmented/Mixed Reality
  * 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
  * Any other novel applications

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

Important Dates:
===============
  * Workshop proposals: September 15, 2018
  * Workshop notification: October 1, 2018
  * Paper submission: October 1, 2018
  * Notification of acceptance: November 20, 2018
  * Camera ready due: January 20, 2019 
  * Author registration due:  January 20, 2019


General Co-Chairs:
===============
Mohan Kankanhalli, National University of Singapore, Singapore
Rainer Lienhart, Universitat Augsburg, Germany
Chengcui Zhang, University of Alabama, USA


Program Co-Chairs:
===============
Min Chen, University of Washington, USA
Leonel Sousa, Universidade de Lisboa, Portugal
Guan-Ming Su, Dolby Labs, USA
Yonghong Tian, Beijing University, China

--

Top

Call for Papers

IWSDS 2019 Special Session -- Dialogue systems and lifelong learning
April 24-26, 2019
Siracusa, Sicily, Italy

* DSLL description

The topic of dialogue systems and chatbots has been gaining renewed interest in the recent years, particularly thanks to the recent development of deep neural networks. Nevertheless, most of the proposed approaches require a very large amounts of data, which is difficult to obtain when talking about dialogue. Proposing Methods that fill the data gap will allow data-driven dialogue systems trained in a specific domain and task to improve over time, and even learning in a cumulative way new domains or tasks is of great interest to fill the data gap. This direction of research is called lifelong learning or continuous learning. From another angle, another research paradigm that allows for continuous learning is to design systems are able to learn a new task or domain through interaction as a student with a teacher could do.

The main obective of this special session  is to gather researchers interested in dialogue systems that interact with the users in order to learn about new domains or acquire new knowledge.

We invite submissions on all aspects of dialogue systems, lifelong  and interactive learning.

Topics include but are not limited to:

- Dialogue systems that improve over time
- Intelligent systems that use interaction to gather new information
- Specific techniques that can enable learning through interaction, such as online reinforcement learning, imitation learning, etc.
- Corpora for interactive learning with dialogue
- Demonstration of systems that learn through interaction
- Evaluation methodologies

* Session Committe

Eneko Agirre, University of the Basque Country, Spain
Mark Cieliebak, Zurich University of Applied Sciences, Switzerland
Olivier Galibert, LNE, France
Sahar Ghannay, LIMSI, Univ. Paris Sud, France
Arantxa Otegi, University of the Basque Country, Spain
Anselmo Peñas, Universidad Nacional de Educación a Distancia, Spain
Camille Pradel, Synapse Développement
Sophie Rosset, LIMSI, CNRS, France
Anne Vilnat, LIMSI, Univ. Paris Sud, France

* Important dates

Submission paper: January 15
Author notification: January 25
Camera ready: February 15

For paper submission process, please check the IWSDS 2019 website <https://iwsds2019.unikore.it/> and the submission paper website <https://easychair.org/conferences/?conf=iwsds2019>

* Background

Artificial intelligence has made significant advances on solving prediction and dialogue tasks. But most of the approaches are based on off-line and supervised learning, where  algorithms take as input annotated data and build a model. Further work is necessary to build autonomous agents which are capable of learning from the environment and the interactions, without explicit supervision for each new task. The goal of Lifelong Learning (LL, also known as Learning to Learn) is to research methods for continuous learning of various tasks over time and learning commonalities among them (Chen and Liu, 2018). Current LL systems exploit similarities between the learned models for past tasks using task meta-features (Eaton and Ruvolo, 2013) and corresponding methods to learn representations of tasks, using for instance neural networks and ensembles of learners. Still, LL assumes that manual annotations exist for each item to be learned, while autonomous agents rarely have access to!
  such supervision. In a realistic scenario the agent receives feedback only after completing a complex task comprising of several decisions, and needs to guess which of the decisions were correct or incorrect.

Current interactions between humans and computers are limited to constrained dialogues, where dialogue systems (aka ChatBots or Conversational Agents?) are trained on a number of annotated sample dialogues of a narrow domain. The development cost is considerable, both in building the representation of the knowledge for the target domain and in the dialogue management proper, where one of the most important shortcomings is the variability of human language and the large amount of background knowledge that needs to be shared for effective dialogue. In addition, most of the learned knowledge needs to be learned nearly from scratch for each new dialogue task, including both the domain knowledge (learned using knowledge induction or knowledge bases) and the dialogue management module (adapted to the new domain). Interestingly, humans use dialogue to improve their own knowledge of a domain. That is, people interact with other people in order to confirm, retract or refine their u!
 nderstanding. This topic of learning through dialogue is an emerging one with more and more attempts to propose framework and tasks to evaluate such system. Most recent work in this area concern learning through conversation where the supervision part is given by the user feedback (Weston, 2016), the way the learning system can ask questions in an online reinforcement learning framework (Li et al., 2017) and also on how to learn and infer new knowledge during a dialogue (Mazumder et al., 2018 ; Letard et al., 2016).

This special session will focus on methods and evaluation methodologies for learning through dialogue. All aspects involved in dialogue (natural language understanding, dialogue management, natural language generation, knowledge management) are of interest.

This special session will provide a focal point for the growing research community on interactive learning with and by dialogue.

** References


Z. Chen, and B. Liu. Lifelong Machine Learning (2nd Edition). Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers. August 2018, 207p

E. Eaton and P. L. Ruvolo. 2013. ELLA: An efficient lifelong learning algorithm. In ICML 2013.

Sahisnu Mazumder, Nianzu Ma, Bing Liu. Towards a Continuous Knowledge Learning Engine for Chatbots. arXiv:1802.06024 [cs.CL], 16 Feb. 2018.

Jiwei Li, Alexander H. Miller, Sumit Chopra, Marc'Aurelio Ranzato, Jason Weston, Learning through Dialogue Interactions by Asking Questions, ICLR 2017.

Jason E. Weston. Dialog-based language learning. NIPS 2016.

Vincent Letard, Sophie Rosset, Gabriel Illouz. Incremental Learning From Scratch Using Analogical Reasoning. ICTAI 2016.

Top

CALL FOR PAPERS
IWSDS 2019: International Workshop on Spoken Dialogue 
Systems Technology
Place: Siracusa, Sicily, Italy
Main Conference Dates: April 24-26, 2019
Web site: https://iwsds2019.unikore.it/

https://easychair.org/cfp/IWSDS2019 

http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=80840&copyownerid=128361 

========================================

The  INTERNATIONAL WORKSHOP ON SPOKEN DIALOGUE SYSTEMS 
TECHNOLOGY (IWSDS) 2019 invites paper submissions in any 
topic related to the main conference theme 'Increasing 
naturalness and flexibility in spoken dialogue 
interaction:'

* Dialogue systems and reasoning
* Machine learning methods for spoken dialogue systems
* Multi-party and multi-lingual dialogue systems
* Open and multi domain systems
* Engagement and emotion in human-robot interactions
* Spoken dialog systems for low-resource languages
* Big data and large scale spoken dialogue systems
* Domain Transfer and adaptation techniques for spoken 
dialog systems
* Spoken dialogue systems applications
* Connecting spoken dialogue systems to global AI
* Personalized conversational agents
* Human-Robot dialogue systems
* Resources for creating dialogue systems
* Multimodal dialogue systems
* Reasoning and Q&A through dialogue interactions

However, submissions are not limited to these topics, and 
submission of papers in all areas of spoken dialogue 
systems is encouraged. We particularly welcome papers that 
can be illustrated by a demonstration, and will organize 
the conference in order to best accommodate these papers, 
whatever their category.

As usual, a selection of accepted papers will be published 
in a book by Springer following the conference (Springer 
LNEE series, SCOPUS and other important indexes).

Authors are requested to submit PDF files of their 
manuscripts using the paper submission system: 
https://easychair.org/conferences/?conf=iwsds2019

We distinguish between the following categories of 
submissions:

* Long Research Papers are reserved for reports on mature 
research results. The expected length of a long paper 
should be in the range of 8-12 pages, including 
references.
* Short Research Papers should be in the range of 4-6 
pages, including references. Authors may choose this 
category if they wish to report on smaller case studies or 
ongoing but interesting and original research efforts.
* Position Papers deal with novel research ideas or 
view-points which describe trends or fruitful starting 
points for future research and elicit discussion and are 
not much researched. They should be 2 pages long, 
excluding references.
* Demo Submissions - System Papers: Authors who wish to 
demonstrate their system may choose this category and 
provide a description of their system and demo. System 
papers should not exceed 6 pages in total.

IWSDS 2019 requires that all authors wishing to present a 
paper take into account:

* The paper is substantially original and will not be 
submitted to any other conference or journal during the 
IWSDS 2019 review period.
* The paper does not contain any plagiarism.
* The paper will be presented by one of the authors 
in-person at the conference site according to the schedule 
published. Any paper accepted in the technical program, 
but not presented on-site will be withdrawn from the 
official conference proceedings.

----------------------------------------------------
Important dates:

Paper submission deadline: December 10, 2018
Acceptance/rejection notification: January 25, 2019
Camera-ready paper due: February 15, 2019
Early bird registration deadline: February 26, 2019
Conference dates: April 24-26, 2019
----------------------------------------------------

Templates for formatting are available on the conference 
website: https://iwsds2019.unikore.it

* Latex Style and Template: 
https://iwsds2019.unikore.it/resources/svmult.zip
* Word Template: 
https://iwsds2019.unikore.it/resources/T1-book.zip
* Requirements for submitting figures that are acceptable: 
https://iwsds2019.unikore.it/resources/Art_Guidelines.pdf

For more information, you can visit the official website 
of the conference: https://iwsds2019.unikore.it/


General Chairs
   Sabato Marco Siniscalchi
   Haizhou Li (Curtesy Assistant)

Technical Program Chairs
    Sandro Cumani
    Valerio Mario Salerno

Top

ESANN 2019: European Symposium on Artificial Neural Networks,

Computational Intelligence and Machine Learning

Bruges, Belgium, 24-25-26 April 2019 

http://www.esann.org/

Call for papers

The call for papers is available at http://www.esann.org/.  The deadline for submitting papers is November 19, 2018.

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:

- Streaming data analysis, concept drift and analysis of dynamic data sets

- Embeddings and Representation Learning for Structured Data

- Parallel and Distributed Machine Learning: Theory and Applications

- Societal Issues in Machine Learning: When Learning from Data is Not Enough

- Reliable Machine Learning

- Statistical physics of learning and inference

- 60 Years of Weightless Neural Systems

ESANN 2019 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 center, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum.

We hope to receive your submission to ESANN 2019 and to see you in Bruges next year!

-----------------------------------------------------

If you do not wish to receive mailings about ESANN conferences, please fill the following form and send it to esann@uclouvain.be (do not reply to this e-mail!):

Name: ....................

First Name: ....................

E-mail address: ....................

Tick one of the following boxes:

O I do not wish to receive any mailing (both printed and e-mails) about the ESANN conference

O I do not wish to receive emails about the ESANN conference, but I accept to receive the printed versions of the call for papers and program (maximum 2 postal mails per year)

O I do not wish to receive postal mails about the ESANN conference, but I accept to receive e-mails (maximum 3 per year)

-----------------------------------------------------

========================================================

ESANN - European Symposium on Artificial Neural Networks,

Computational Intelligence and Machine Learning

http://www.esann.org/

* For submissions of papers, reviews, registrations:

Michel Verleysen

Univ. Cath. de Louvain - Machine Learning Group

Top

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
12-17 May 2019 ? Brighton, UK
Special Session Proposal Deadline: 20 August 2018
Tutorial Proposal Deadline: 22 October 2018
Paper Submissions Deadline: 29 October 2018
Signal Processing Letters Deadline: 14 January 2019
Sponsored by IEEE SPS

Top

Appel Ateliers: JPC 2019

16 mai 2019

Université de Mons, Belgique

Objectifs

Afin d?encourager le dialogue et les rencontres entre cliniciens et chercheurs, le comité d?organisation des JPC 2019 lance un appel à l?organisation d?ateliers transversaux, ciblés sur une thématique particulière. Ces ateliers seront co-organisés par au moins un(e) clinicien(ne) et un(e) chercheur(se) sous une forme ouverte et participative, p.ex. table ronde, débat, tutoriel, session de démonstration, séminaires...

Quatre ateliers prendront place la matinée du jeudi 16 mai 2019 lors de la dernière journée des 8e Journées de Phonétique Clinique. Ils disposeront d?un créneau de 3 heures au maximum. L?organisation des ateliers sera confiée aux responsables des projets d?atelier acceptés. Ceux-ci seront chargés d?assurer la sollicitation des intervenants ou l?appel à communications, la définition du programme scientifique et la communication avec les participants à l?atelier. Ils devront s'assurer de l'inscription à l?atelier des participants, inscrits ou non-inscrits aux JPC. Les organisateurs des JPC prendront en charge la partie logistique des ateliers (gestion des salles, pauses café et diffusion des abstracts dans le livre des résumés de la conférence). Les invitations dans le cadre de ces ateliers ne seront pas prises en charge par l?organisation des JPC 2019.

Calendrier

?  Date des ateliers : jeudi 16 mai 2019

?  Date limite de soumission de la proposition : 18 janvier 2019

?  Réponse du comité d'organisation des JPC : 25 janvier 2019

Modalités de proposition

Les propositions d'ateliers (2 pages maximum) comprendront les éléments suivants :

?       Titre de l'atelier

?       Nom, prénom, affiliation, adresse électronique des responsables de l?atelier (au moins un(e) clinicien(ne) et un(e) chercheur(se))

?       Nom, prénom et coordonnées de la personne de contact pour la communication avec les organisateurs

?       Une description synthétique de la thématique de l'atelier

?       Le format envisagé (table ronde, débat, tutoriel, session de démonstration, séminaires, etc.)

?       Comité scientifique

?       Participants invités ou attendus (nombre, profil: enseignants, chercheurs, cliniciens, étudiants, etc.)

Les propositions seront envoyées en format pdf à l?adresse suivante: JPC2019@umons.ac.be  

Elles seront soumises à l?avis du comité de programme des JPC 2019.

Publication dans le livret des résumés

Le format souhaité suivra les recommandations des JPC 2019 (résumé de maximum 400 mots en français (hors titre, auteurs, et bibliographie)

Contact et informations

JPC2019@umons.ac.be  

www.langage.be/JPC/indexjpc.html 

Top

****************************

Appel Ateliers: JPC 2019

16 mai 2019

Université de Mons, Belgique

****************************

Objectifs

Afin d?encourager le dialogue et les rencontres entre cliniciens et chercheurs, le comité d?organisation des JPC 2019 lance un appel à l?organisation d?ateliers transversaux, ciblés sur une thématique particulière. Ces ateliers seront co-organisés par au moins un(e) clinicien(ne) et un(e) chercheur(se) sous une forme ouverte et participative, p.ex. table ronde, débat, tutoriel, session de démonstration, séminaires...

Quatre ateliers prendront place la matinée du jeudi 16 mai 2019 lors de la dernière journée des 8e Journées de Phonétique Clinique. Ils disposeront d?un créneau de 3 heures au maximum. L?organisation des ateliers sera confiée aux responsables des projets d?atelier acceptés. Ceux-ci seront chargés d?assurer la sollicitation des intervenants ou l?appel à communications, la définition du programme scientifique et la communication avec les participants à l?atelier. Ils devront s'assurer de l'inscription à l?atelier des participants, inscrits ou non-inscrits aux JPC. Les organisateurs des JPC prendront en charge la partie logistique des ateliers (gestion des salles, pauses café et diffusion des abstracts dans le livre des résumés de la conférence). Les invitations dans le cadre de ces ateliers ne seront pas prises en charge par l?organisation des JPC 2019.

Calendrier

?  Date des ateliers : jeudi 16 mai 2019

?  Date limite de soumission de la proposition : 18 janvier 2019

?  Réponse du comité d'organisation des JPC : 25 janvier 2019

Modalités de proposition

Les propositions d'ateliers (2 pages maximum) comprendront les éléments suivants :

?       Titre de l'atelier

?       Nom, prénom, affiliation, adresse électronique des responsables de l?atelier (au moins un(e) clinicien(ne) et un(e) chercheur(se))

?       Nom, prénom et coordonnées de la personne de contact pour la communication avec les organisateurs

?       Une description synthétique de la thématique de l'atelier

?       Le format envisagé (table ronde, débat, tutoriel, session de démonstration, séminaires, etc.)

?       Comité scientifique

?       Participants invités ou attendus (nombre, profil: enseignants, chercheurs, cliniciens, étudiants, etc.)

Les propositions seront envoyées en format pdf à l?adresse suivante: JPC2019@umons.ac.be  

Elles seront soumises à l?avis du comité de programme des JPC 2019.

Publication dans le livret des résumés

Le format souhaité suivra les recommandations des JPC 2019 (résumé de maximum 400 mots en français (hors titre, auteurs, et bibliographie)

Contact et informations

JPC2019@umons.ac.be  

www.langage.be/JPC/indexjpc.html 

Top

Call for papers: 14^th PAC conference

(Phonologie de l’Anglais Contemporain / Phonology of Contemporary English)

PAC AIX 2019

Phonetic and phonological variation in contemporary English:

Xperience-Xperimentation

Laboratoire Parole et Langage, Aix-en-Provence, France

June 4-5 2019

Guest Speakers : Dominic Watt (U. York)

&

Emmanuel Ferragne (U. Paris Diderot)

We are pleased to announce the 2019 edition of the annual PAC conference, ‘Phonetic and phonological variation in contemporary English: Xperience / Xperimentation’, due to take place from Tuesday June 4 to Wednesday June 5 2019 and, hosted by the Laboratoire Parole et Langage and Aix-Marseille University in Aix-en-Provence. We shall welcome as invited guest speakers Dominic Watt, from the University of York and Emmanuel Ferragne from  The Paris Diderot University of Paris Diderot. Both have worked on varieties of English and are currently working on forensic phonetics, among other topics.

The PAC programme (http://www.pacprogramme.net) gathers researchers interested in the study of variation in contemporary spoken English, adhering to a common protocol for data collection and annotation. The PAC conferences have been organized annually since 2000 and have been willing to welcome researchers studying spoken English worldwide and from a wide variety of backgrounds.

The 2019 edition of the conference will focus on « experience/experimentation », in French « l’expérience » (which is polysemic). People working in the framework of the PAC programme are used to following a field approach. The data collected within the framework of the PAC programme may easily be exploited by experimentalists as well. The idea is to open the conference to researchers working in a more experimental setting. We would like to make the link between the 2 two domains and our guest speakers will show that the two approaches may be complementary in the study of language. Papers concerned by either field work or experimental methods or combining the two domains are welcome. A wide range of issues can be explored, matching the research axes of the PAC programme, such as,  and among others, studies of English in urban contexts, analyses of prosodic variation, of L2 English or papers concerned with tools and annotation strategies..

The audience will consist of colleagues and students working on spoken English corpora and the presentations are all in English.

The deadline for sending a title with a one-page anonymous abstract (excluding references) is January 7, 2019.

Please visit the conference web site, where you can find a template for abstracts and upload your abstract submission: https://pacaix2019.sciencesconf.org/ (you will need to create a sciencesconf account if you don’t already have one).

Notification of acceptance will be sent by mid February 2019.

For any questions, you can contact us at the following address: pacaix2019@sciencesconf.org

Local Organising committee:

Julia Bongiorno

Stéphanie Desous

Sophie Herment

Joëlle Lavaud

Catherine Perrot

Claudia Pichon-Starke

Paul Sartre

Anne Tortel

Gabor Turcsan

Top

22^nd Rencontres Jeunes Chercheurs (RJC 2019 - ED 268)

?Variation in linguistics: approaches, data, uses?

6^th? 7^thJune 2019

University Sorbonne Nouvelle - Paris 3 (Maison de la Recherche) 

4, rue des Irlandais - 75005 PARIS

Dear Colleagues,

The «Langage et langues : description, théorisation, transmission» Doctoral School (ED 268, University Sorbonne Nouvelle) is glad to announce the Rencontres Jeunes Chercheurs (RJC 2019). The conference will be held from June 6^th- June 7^th 2019 in Paris.

These Rencontres offer junior researchers preparing a Master?s or a Doctorate degree, as well as post-doctorate students, the opportunity to present their work in individual paper or poster sessions.

This year?s theme tackles the issue of:

?Variation in linguistics: approaches, data, uses?

We encourage proposals concerned with this topic from any linguistic discipline. Everyone who is interested in presenting an individual paper or a poster is welcome to submit a 4000 characters abstract in English or French for double-blind review by January 21^st, 2019 at 7pm (Paris time UTC+1). Abstracts must be uploaded on the platform EasyChair at the following address: https://easychair.org/conferences/?conf=rjc2019

Individual papers will be allocated 20 minutes, and an additional 10 minutes for discussion.

The size of the posters is A0. Poster authors will be invited to give a short oral presentation of their work.

Agenda

Submission deadline: January 21^st, 2019

Notification of acceptance: March 2019

Conference dates: June 6^th ? 7^th, 2019

Conference location: Maison de la Recherche

Address: 4, rue des Irlandais - 75005 PARIS

Web site: http://www.univ-paris3.fr/rencontres-jeunes-chercheurs-301310.kjsp

Please find attached the call for papers and submission guidelines (in French and in English) for the Rencontres Jeunes Chercheurs. 

Please, circulate widely. Many thanks in advance.

Best regards,

---

The RJC Organizing Committee

rjc-ed268@univ-paris3.fr

Top

ACM SIGIR 2019

The 42nd International ACM SIGIR Conference on

Research and Development in Information Retrieval

July 21-25, 2019, Paris, France

CALL FOR PAPERS

Call for Full Papers

The annual SIGIR conference is the major international forum for the presentation of new research results, and the demonstration of new systems and techniques, in the broad field of information retrieval (IR). The 42nd ACM SIGIR conference, to be held in Paris, France, welcomes contributions related to any aspect of information retrieval and access, including theories, foundations, algorithms, applications, evaluation, and analysis. The conference and program chairs invite those working in areas related to IR to submit original papers for review.

Important Dates  (timezone: anywhere on earth)

Committees

Program chairs

• Yoelle Maarek, Amazon Research, Haifa, Israel
• Jian-Yun Nie, University of Montreal, Canada
• Falk Scholer, RMIT University, Melbourne, Australia

General chairs

• Max Chevalier, CNRS &  Université Paul Sabatier, Toulouse, France
• Eric Gaussier, CNRS & Université Joseph Fourier, Grenoble, France
• Benjamin Piwowarski, CNRS, LIP6, Sorbonne Université, Paris, France

Contact

All questions about full paper submissions should be emailed to sigir2019-pcchairs AT easychair DOT org.

follow us on twitter : @sigir2019

follow us on our web site : http://sigir.org/sigir2019/

Top

HISTORY: On July 20, 1969 at 20:17 UTC, Earth witnessed one of the most challenging technology accomplishments by mankind to date of NASA Apollo-11 with over 600M people witnessing both the landing and first steps on the moon by Neil Armstrong and Buzz Aldrin. Next July 2019 marks the 50^th Anniversary of the historical Apollo-11 lunar landing and first steps. https://en.wikipedia.org/wiki/Apollo_11

NSF CRSS-UTDallas Project: With support from the US National Science Foundation (NSF-CISE), CRSS-UTDallas has spent the last six years developing a hardware/software solution to digitize and recover all 30-track analog tapes from Apollo-11 (plus Apollo-13 and other missions), as well as development of speech diarization technologies to advance speech technology for such data. A total of 19,000 hours of data consisting of all NASA air-to-ground, mission control, and backroom support team discussions was released this year (news releases from this NSF sponsored project this year include: NSF, NASA, BBC, AIP (Acoustical Society of America), NPR, many on-line news sites, and involvement in a planned CNN documentary where this data is contributing, etc.). To date, this will be the largest publically available audio corpus of time synchronized, team based (~600 people) naturalistic communications to accomplish a real-world task.

ANNOUNCEMNT: This email is to announce the release of the FEARLESS STEPS CHALLENGE corpus, which is being shared for a proposed Special Session at ISCA INTERSPEECH-2019. The attached flyer details the 5 challenge tasks involved:

1. SAD: Speech Activity Detection

2. Speaker Diarization

3. SID: Speaker Identification

4. ASR: Automatic Speech Recognition

5. Sentiment Detection

This challenge corpus consists of 100hours from 5 of the 30-track channels spanning three phases of Apollo-11 mission: (i) lift off, (ii) landing, (iii) lunar walk. All data for this challenge will be available soon via a download option for all to participate (this site has sample audio from the NSF funded project: https://app.exploreapollo.org/ ). In addition, any lab/group wishing to have access to the entire 19,000 hours can do so without charge (this is public data, so it will be available via download, or a small fee for a hard-disk and shipping to your lab).   

While diarization efforts in the past have concentrated on single channel broadcast news, interviews, etc. These all represent typically a single speaker, or small group discussing topics of interest. The FEARLESS STEPS CORPUS is all time synchronized (with IRIG Time Channel) across 30 channels, with loops containing anywhere from 3-33 speakers working collaboratively to solve challenging problems. CRSS-UTDallas has produced full diarization output for the entire 19,000hrs of data (SAD, SID, DIAR/ASR) which is available with the corpus.

REQUEST:  We are proposing a Special Session at ISCA INTERSPEECH-2019. If you have interest in getting access to the FEARLESS STEPS CORPUS and potentially participating in the CHALLENGE, please reply to this email Hansen, John' <john.hansen@utdallas.edu>(an expression of interest does not obligate you to submit, we are simply trying to collect a list of interested researchers for the data). 

Many thanks for your interest!

CRSS-UTDallas Fearless Steps Team

Top

2019 Jelinek Summer Workshop on Speech and Language Technology

We are pleased to invite one page research proposals for a workshop on Machine Learning for Speech and Language Technology at ÉTS (École de Technologie Supérieure) in Montreal, CA June 24 to August 2, 2019 (Tentative)

CALL FOR PROPOSALS Deadline: Monday, November 5th, 2018.
 
One-page proposals are invited for the annual Frederick Jelinek Memorial Workshop in Speech and Language Technology. Proposals should aim to advance the state of the art in any of the various fields of Human Language Technology (HLT) or related areas of Machine Intelligence, including Computer Vision and Healthcare. Proposals may address emerging topics or long-standing problems. Areas of interest in 2019 include but are not limited to: * SPEECH TECHNOLOGY: Any aspect of information extraction from speech signals; techniques that generalize in spite of very limited amounts of training data and/or which are robust to input signal variations ; techniques for processing of speech in harsh environments, etc.
 * NATURAL LANGUAGE PROCESSING: Knowledge discovery from text; new approaches to traditional problems such as syntactic/semantic/pragmatic analysis, machine translation, cross - language information retrieval, summarization, etc.; domain adaptation; integrated language and social analysis; etc.
 * MULTIMODAL HLT: Joint models of text or speech with sensory data; grounded language learning; applications such as visual question - a nswering, video summarization, sign language technology, multimedia retrieval, analysis of printed or handwritten text. * DIALOG AND LANGUAGE UNDERSTANDING: U n d e r s t a n din g h u m a n - to - h u m a n o r h u m a n - to - computer conversation; dialog manag ement; naturalness of dialog (e.g. sentiment analysis).
 * LANGUAGE AND HEALTHCARE: information extraction from electronic health records; speech and language technology in health monitoring; healthcare delivery in hospitals or the home, public health, etc.
 These workshops are a continuation of the Johns Hopkins University CLSP summer workshop series, and will be hosted by various partner universities on a rotating basis. The research topics selected for investigation by teams in past workshops should serve as good examples for prospective proposers: http://www.clsp.jhu.edu/workshops/. An independent panel of experts will screen all received proposals for suitability. Results of this screening will be communicated by November 9th, 2018. Authors passing this initial screening will be invited to an interactive peer-review meeting in Baltimore on December 7-9th, 2018. Proposals will be revised at this meeting to address any outstanding concerns or new ideas. Two or three research topics and the teams to tackle them will be selected at this meeting for the 2019 workshop. We attempt to bring the best researchers to the workshop to collaboratively pursue research on the selected topics. Each topic brings together a diverse team of researchers and students. Authors of successful proposals typically lead these teams. Other senior participants come from academia, industry and government. Graduate student participants familiar with the field are selected in accordance with their demonstrated performance. Undergraduate participants, selected through a national search, are rising star seniors: new to the field and showing outstanding academic promise. If you are interested in participating in the 2019 Summer Workshop we ask that you submit a one-page research proposal for consideration, detailing the problem to be addressed. If a topic in your area of interest
is chosen as one of the topics to be pursued next summer, we expect you to be available to participate in the six - week workshop . We are not asking for an ironclad commitment at this juncture, just a good faith commitment that if a project in your area of interest is chosen, you will actively pursue it. We in turn will make a good faith effort to accommodate any personal/logistical needs to make your six-week participation possible.
 
Proposals must be submitted to jsalt2019-planning@jhu.edu by 23:59PM EDT on Monday, 11/05/2018. 

Top

Zero Resource Speech Challenge 2019: TTS without T

Top

*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*

ASVspoof 2019 CHALLENGE:
Future horizons in spoofed/fake audio detection
http://www.asvspoof.org/ 
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=

Can you distinguish computer-generated or replayed speech from authentic/bona fide speech? Are you able to design algorithms to detect spoofs/fakes automatically?

Are you concerned with the security of voice-driven interfaces?

Are you searching for new challenges in machine learning and signal processing?

Join ASVspoof 2019 ? the effort to develop next-generation countermeasures for the automatic detection of spoofed/fake audio. In combining the forces of leading research institutes and industry, ASVspoof 2019 encompasses two separate sub-challenges in logical and physical access control, and provides a common database of the most advanced spoofing attacks to date. The aim is to study both the limits and opportunities of spoofing countermeasures in the context of automatic speaker verification and fake audio detection.

CHALLENGE TASK

Given a short audio clip, determine whether it represents authentic/bona fide human speech, or a spoof/fake (replay, synthesized speech or converted voice). You will be provided with a large database of labelled training and development data and will develop machine learning and signal processing countermeasures to distinguish automatically between the two. Countermeasure performance will be evaluated jointly with an automatic speaker verification (ASV) system provided by the organisers.

BACKGROUND:
The ASVspoof 2019 challenge follows on from two previous ASVspoof challenges, held in 2015 and 2017. The 2015 edition focused on spoofed speech generated with text-to-speech (TTS) and voice conversion (VC) technologies. The 2017 edition focused on replay spoofing. The 2019 edition is the first to address all three forms attack and the latest, cutting-edge spoofing attack technology.

ADVANCES:

Today?s state-of-the-art, TTS and VC technologies produce speech signals that are as good as perceptually indistinguishable from bona fide speech. The LOGICAL ACCESS sub-challenge aims to determine whether the advances in TTS and VC pose a greater threat to the reliability of automatic speaker verification and spoofing countermeasure technologies. The PHYSICAL ACCESS sub-challenge builds upon the 2017 edition with a far more controlled evaluation setup which extends the focus of ASVspoof to fake audio detection in, e.g. the manipulation of voice-driven interfaces (smart speakers).

METRICS:

The 2019 edition also adopts a new metric, the tandem detection cost function (t-DCF). Adoption of the t-DCF metric aligns ASVspoof more closely to the field of ASV. The challenge nonetheless focuses on the development of standalone spoofing countermeasures; participation in ASVspoof 2019 does NOT require any expertise in ASV. The equal error rate (EER) used in previous editions remains as a secondary metric, supporting the wider implications of ASVspoof involving fake audio detection.

SCHEDULE:

Training and development data release: 19th December 2018

Evaluation data release: 15th February 2019

Deadline to submit evaluation scores: 22nd February 2019

Organisers return results to participants: 15th March 2019

INTERSPEECH paper submission deadline: 29th March 2019

REGISTRATION:

Registration should be performed once only for each participating entity and by sending an email to registration@asvspoof.org with ?ASVspoof 2019 registration? as the subject line. The mail body should include: (i) the name of the team; (ii) the name of the contact person; (iii) their country; (iv) their status (academic/non-academic), and (v) the challenge scenario(s) for which they wish to participate (indicative only). Data download links will be communicated to registered contact persons only.

MAILING LIST:

Subscribe to general mailing list by sending e-mail with subject line ?subscribe asvspoof2019? to sympa@asvspoof.org. To post messages to the mailing list itself, send e-mails to asvspoof2019@asvspoof.org

ORGANIZERS^*:

Junichi Yamagishi, NII, Japan & Univ. of Edinburgh, UK

Massimiliano Todisco, EURECOM, France

Md Sahidullah, Inria, France

Héctor Delgado, EURECOM, France

Xin Wang, National Institute of Informatics, Japan

Nicholas Evans, EURECOM, France

Tomi Kinnunen, University of Eastern Finland, Finland

Kong Aik Lee, NEC, JAPAN

Ville Vestman, University of Eastern Finland, Finland

* Equal contribution

CONTRIBUTORS:

University of Edinburgh, UK; Nara Institute of Science and Technology, Japan, University of Science and Technology of China, China; iFlytek Research, China; Saarland University / DFKI GmbH, Germany; Trinity College Dublin, Ireland; NTT Communication Science Laboratories, Japan; HOYA, Japan; Google LLC (Text-to-Speech team, Google Brain team, Deepmind); University of Avignon, France; Aalto University, Finland; University of Eastern Finland, Finland; EURECOM, France.

FURTHER INFORMATION:

info@asvspoof.org

Top

Dialog System Technology Challenge 7 (DSTC7)
Call for Participation: Data distribution has been started
Website: http://workshop.colips.org/dstc7/index.html

========================================

Background
-----------------
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 three parallel tracks by peer-reviews:

- Sentence Selection Track
- Sentence Generation Track
- Audio Visual Scene-aware dialog (AVSD) Track

Participation is welcomed from any research team (academic, corporate,
non-profit, government).

Important Dates
------------------------
- Jun 1, 2018: Training data is released
- Sep 10, 2018: Test data is released
- Sep 24, 2018: Entry submission deadline
- Oct or Nov 2018: Paper submission deadline
- Spring 2019: DSTC7 special session or workshop (venue: TBD)

DSTC7 Organizing Committee
--------------------------------------------
- Koichiro Yoshino - Nara Institute of Science and Technology (NAIST), Japan
- Chiori Hori - Mitsubishi Electric Research Laboratories (MERL), USA
- Julien Perez - Naver Labs Europe, France
- Luis Fernando D'Haro - Institute for Infocomm Research (I2R), Singapore

DSTC7 Track Organizers
-------------------------------------
Sentence Selection Track:
- Lazaros Polymenakos - IBM Research, USA
- Chulaka Gunasekara - IBM Research, USA
- Walter S. Lasecki - University of Michigan, USA
- Jonathan Kummerfeld - University of Michigan, USA

Sentence Generation Track:
- Michel Galley - Microsoft Research AI&R, USA
- Chris Brockett - Microsoft Research AI&R, USA
- Jianfeng Gao - Microsoft Research AI&R, USA
- Bill Dolan - Microsoft Research AI&R, USA

Audio Visual Scene-aware dialog (AVSD) Track:
- Chiori Hori - Mitsubishi Electric Research Laboratories (MERL), USA
- Tim K. Marks - Mitsubishi Electric Research Laboratories (MERL), USA
- Devi Parikh - Georgia Tech, USA
- Dhruv Batra - Georgia Tech, USA

DSTC Steering Committee
---------------------------------------
- Jason Williams - Microsoft Research (MSR), USA
- Rafael E. Banchs - Institute for Infocomm Research (I2R), Singapore
- Seokhwan Kim - Adobe Research, USA
- Matthew Henderson - PolyAI, Singapore
- Verena Rieser - Heriot-Watt University, UK

Contact Information
---------------------------------------
Join the DSTC mailing list to get the latest updates about DSTC7:

- To join the mailing list: send an email to
listserv@lists.research.microsoft.com and put 'subscribe DSTC' in the
body of the message (without the quotes).
- To post a message: send your message to dstc@lists.research.microsoft.com.

For specific enquiries about DSTC7:
- Please feel free to contact any of the Organizing Committee members
directly.

Top

ELRA is very pleased to announce that the 12th edition of the Language Resources and
Evaluation Conference, LREC 2020,  will take place in Marseille (France) on May 11-16,
2020.
More information will be published on the conference website (online soon).

Best wishes,
Helene Mazo
on behalf of the LREC 2020 Programme Committee

www.lrec-conf.org
Follow us on Twitter: @LREC2020

Top

Dear SProSIG Members,

We are pleased to announce that the 2020 Speech Prosody conference

will be held in Tokyo, tentatively in late May or early June.

Also, there are two upcoming special sessions relating to prosody, at

ICPhs 2019, with submission deadlines for both of December 4:

'Interacting Channels of Speech - Tune and Text'

https://timo-roettger.weebly.com/icphs---tune-and-text.html and

'Modeling Meaning-Bearing Configurations of Prosodic Features'

http://www.cs.utep.edu/nigel/pconstructions/icphs-configs.html .

We'd also like to take this opportunity to introduce ourselves, the

incoming officers of SProSig for 2018-2020: namely Martine Grice,

Plinio Barbosa, Hongwei Ding, Aoju Chen and myself.  We look forward

to serving the membership and are eager to hear your ideas and

suggestions.

Finally, the SProSIG mailing list is now hosted at the University of

Texas at El Paso. Subscription/unsubscription instructions are below.

Mailings will continue to be infrequent and focus on conference

announcements and the like. If you have such information to share,

please contact any of us.

Hongwei Ding, Aoju Chen, Martine Grice, Plinio Barbosa, Nigel Ward

Speech Prosody Special Interest Group  www.sprosig.org

This mail was sent through the SProSIG mailing list, which is for

announcements of interest to the speech prosody research community.

Subscribe/unsubscribe at http://listserv.utep.edu/mailman/listinfo/sprosig

Nigel Ward, Professor of Computer Science, University of Texas at El Paso

CCSB 3.0408,  +1-915-747-6827

nigel@utep.edu    http://www.cs.utep.edu/nigel/   

Top