ISCA - International Speech
Communication Association


ISCApad Archive  »  2022  »  ISCApad #294  »  Events

ISCApad #294

Saturday, December 10, 2022 by Chris Wellekens

3 Events
3-1 ISCA Events
3-1-1(2023-08-20) Call for Special Sessions/Challenges Interspeech 2023 Dublin, Ireland

Call for Special Sessions/Challenges

We are delighted to announce the launch of the Call for Special Sessions/Challenges for INTERSPEECH 2023 in Dublin, Ireland in August 2023.

 

Submissions are encouraged 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’s theme, Inclusive Spoken Language Science and Technology, are particularly welcome. Apart from supporting a particular theme, special sessions may also have a different format from a regular session.

 

Check out https://www.interspeech2023.org/special-sessions-challenges/ for more information, including how to submit your proposal.

 

Important Dates

Proposals of special sessions/challenges due       9th November 2022

Notification of pre-selection       14th December 2022

Final list of special sessions         17th May 2023

For all updates on INTERSPEECH 2023, refer to our website at https://www.interspeech2023.org/

Top

3-1-2(2023-08-20) INTERSPEECH 2023 First Call for Papers

INTERSPEECH 2023 First Call for Papers

 

INTERSPEECH is the world’s largest and most comprehensive conference on the science and technology of spoken language processing. INTERSPEECH conferences emphasise interdisciplinary approaches addressing all aspects of speech science and technology, ranging from basic theories to advanced applications.

 

INTERSPEECH 2023 will take place in Dublin, Ireland, from August 20-24th 2023 and will feature oral and poster sessions, plenary talks by internationally renowned experts, tutorials, special sessions and challenges, show & tell, exhibits, and satellite events.

 

The theme of INTERSPEECH 2023 is Inclusive Spoken Language Science and Technology – Breaking Down Barriers. Whilst it is not a requirement to address this theme, we encourage submissions that: report performance metric distributions in addition to averages; break down results by demographic; employ diverse data; evaluate with diverse target users; report barriers that could prevent other researchers adopting a technique, or users from benefitting. This is not an exhaustive list, and authors are encouraged to discuss the implications of the conference theme for their own work.

 

Papers are especially welcome from authors who identify as being under-represented in the speech science and technology community, whether that is because of geographical location, economic status, race, age, gender, sexual orientation or any other characteristic.

Paper Submission

INTERSPEECH 2023 seeks original and innovative papers covering all aspects of speech science and technology. The working language of the conference is English, so papers must be written in English. The paper length is up to four pages in two columns with an additional page for references only. Submitted papers must conform to the format defined in the author’s kit provided on the conference website (https://www.interspeech2023.org/), and may optionally be accompanied by multimedia files. Authors must declare that their contributions are original and that they have not submitted their papers elsewhere for publication. Papers must be submitted electronically and will be evaluated through rigorous peer review on the basis of novelty and originality, technical correctness, clarity of presentation, key strengths, and quality of references. The Technical Programme Committee will decide which papers to include in the conference programme using peer review as the primary criterion, with secondary criteria of addressing the conference theme, and diversity across the programme as a whole.

Scientific areas and topics

 

INTERSPEECH 2022 embraces a broad range of science and technology in speech, language and communication, including – but not limited to – the following topics:

 

  • Speech Perception, Production and Acquisition

  • Phonetics, Phonology, and Prosody

  • Paralinguistics in Speech and Language

  • Analysis of Conversation

  • Speech, Voice, and Hearing Disorders

  • Speaker and Language Identification

  • Speech and Audio Signal Analysis

  • Speech Coding and Enhancement

  • Speech Synthesis

  • Spoken Language Generation

  • Automatic Speech Recognition

  • Spoken Dialogue and Conversational AI Systems

  • Spoken Language Translation, Information Retrieval, Summarization

  • Technologies and Systems for New Applications

  • Resources and Evaluation

Technical Program Committee Chairs

Simon King - University of Edinburgh, UK

Kate Knill - University of Cambridge, UK

Petra Wagner - University of Bielefeld, Germany

Contact

For all queries relating to this call for papers, please email:

tpc-chairs@interspeech2023.org

Important dates

Paper Submission Deadline March 1st, 2023

Paper Update Deadline March 8th, 2023

Paper Acceptance Notification May 17th, 2023

Final Paper Upload and Paper Presenter Registration Deadline June 1st, 2023

 

 

 

 

Top

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

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

Top

3-1-4(2024-07-02) 12th Speech Prosody Conference @Leiden, The Netherlands

Dear Speech Prosody SIG Members,

 

Professor Barbosa and I are very pleased to announce that the 12th Speech Prosody Conference will take place in Leiden, the Netherlands, July 2-5, 2024, and will be organized by Professors Yiya Chen, Amalia Arvaniti, and Aoju Chen.  (Of the 303 votes cast, 225 were for Leiden, 64 for Shanghai, and 14 indicated no preference.) 

 

Also I'd like to remind everyone that nominations for SProSIG officers for 2022-2024 are being accepted still this week, using the form at http://sprosig.org/about.html, to Professor Keikichi Hirose.  If you are considering nominating someone, including yourself, feel free to contact me or any current officer to discuss what's involved and what help is most needed.

 

Nigel Ward, SProSIG Chair

Professor of Computer Science, University of Texas at El Paso

CCSB 3.0408,  +1-915-747-6827

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

 

 

Top

3-1-5(2024-09-01) Interspeech 2024, Jerusalem, Israel.

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

September 1 till September 5.

Top

3-1-6ISCA INTERNATIONAL VIRTUAL SEMINARS

 

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

 

https://www.isca-speech.org/iscaweb/index.php/distinguished-lecturers/online-seminars

ISCA INTERNATIONAL VIRTUAL SEMINARS

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

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

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

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

If you make use of this scheme and arrange a seminar, please send brief details (lab, speaker, date) to education@isca-speech.org

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


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

 

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



Top

3-1-7ISCA Workshop - Remembering Sadaoki Furui

ISCA Workshop - Remembering Sadaoki Furui
November 29, 2022, 14h00-16h30 Central European Time
A zoom link for participating in the virtual workshop can be obtained following the information on the ISCA home page from November 15.

Program:

14:00 - Welcome (Chair: Sebastian Möller)

14:10 - Tatsuya Kawahara (Chair: Sebastian Möller)

14:25 - Audio excerpt from IEEE, plus photo collage (Chair: Isabel Trancoso)

14:30 - Shri Narayanan (Chair: Isabel Trancoso)

14:45 - Video excerpt from Saras Institute  (Chair: Julia Hirschberg)

14:50 - Karen Livescu (Chair: Julia Hirschberg)

15:05 - Video excerpt from Maui workshop (Chair: John Hansen)

15:10 - Jean-François Bonastre (Chair: Roger Moore)

15:25  - Panel session open to anyone who registers (Chair: Roger Moore)

16:15 - Closing

 

Organizing Team: 

Julia Hirschberg, Columbia University

Sebastian Möller, TU Berlin

Roger Moore, University of Sheffield

Isabel Trancoso, INESC-ID/IST, Univ. Lisbon

Top

3-1-8Speech Prosody courses

Dear Speech Prosody SIG Members,

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

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

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

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

For details:
  http://www.letras.ufmg.br/padrao_cms/index.php?web=lbass&lang=2&page=3670&menu=&tipo=1
 
 
 
Plinio Barbosa and Nigel Ward

Top

3-2 ISCA Supported Events
3-2-1(2023-01-07) SLT-CODE Hackathon Announcement , Doha, Qatar

SLT-CODE Hackathon Announcement

 

Have you ever asked yourself how your smartphone recognizes what you say and who you are?

 

Have you ever thought about how machines recognize different languages?

 

If that is your case, join us for a two-day speech and language technology hackathon. We will answer these questions and build fantastic systems with the guidance of top language and speech scientists in a collaborative environment.

 

The two-day speech and language technology hackathon will take place during the IEEE Spoken Language Technology (SLT) Workshop in Doha, Qatar, on January 7th and 8th, 2023. This year's Hackathon will be inspiring, momentous, and fun. The goal is to build a diverse community of people who want to explore and envision how machines understand the world's spoken languages.

 

During the Hackathon, you will be exposed (but not limited) to speech and language toolkits like ESPNet, SpeechBrain, K2/Kaldi, Huggingface, TorchAudio, or commercial APIs like Amazon Lex, etc., and you will be hands-on using this technology.

 

At the end of the Hackathon, every team will share their findings with the rest of the participants. Selected projects will have the opportunity to be presented at the SLT workshop.

 

The Hackathon will be at the Qatar Computing Research Institute (QCRI) in Doha, Qatar (GMT+3). In-person participation is preferred; however, remote participation is possible by joining a team with at least one person being local.

 

More information on how to apply and important dates are available at our website https://slt2022.org/hackathon.php

 

Interested? Apply here: https://forms.gle/a2droYbD4qset8ii9 The deadline for registration is September 30th, 2022.

 

If you have immediate questions, don't hesitate to contact our hackathon chairs directly at hackathon.slt2022@gmail.com.

Top

3-3 Other Events
3-3-1(2022-12-13) CfP 18th Australasian International Conference on Speech Science and Technology (SST2022), Canberra, Australia
SST2022: CALL FOR PAPERS

The Australasian Speech Science and Technology Association is pleased to call for papers for the 18th Australasian International Conference on Speech Science and Technology (SST2022). SST is an international interdisciplinary conference designed to foster collaboration among speech scientists, engineers, psycholinguists, audiologists, linguists, speech/language pathologists and industrial partners.

? Location: Canberra, Australia (remote participation options will also be available)
? Dates: 13-16 December 2022
? Host Institution: Australian National University
? Deadline for tutorial and special session proposals: 8 April 2022
? Deadline for submissions: 17 June 2022
? Notification of acceptance: 31 August 2022
? Deadline for upload of revised submissions: 16 September 2022
? Website: www.sst2022.com

Submissions are invited in all areas of speech science and technology, including:

? Acoustic phonetics
? Analysis of paralinguistics in speech and language
? Applications of speech science and technology
? Audiology
? Computer assisted language learning
? Corpus management and speech tools
? First language acquisition
? Forensic phonetics
? Hearing and hearing impairment
? Languages of Australia and Asia-Pacific (phonetics/phonology)
? Low-resource languages
? Pedagogical technologies for speech
? Second language acquisition
? Sociophonetics
? Speech signal processing, analysis, modelling and enhancement
? Speech pathology
? Speech perception
? Speech production
? Speech prosody, emotional speech, voice quality
? Speech synthesis and speech recognition
? Spoken language processing, translation, information retrieval and summarization
? Speaker and language recognition
? Spoken dialog systems and analysis of conversation
? Voice mechanisms, source-filter interactions

We are inviting two categories of submission: 4-page papers (for oral or poster presentation, and publication in the proceedings), and 1-page detailed abstracts (for poster presentation only). Please follow the author instructions in preparing your submission.

We also invite proposals for tutorials, as 3-hour intensive instructional sessions to be held on the first day of the conference. In addition, we welcome proposals for special sessions, as thematic groupings of papers exploring specific topics or challenges. Interdisciplinary special sessions are particularly encouraged.

For any queries, please contact sst2022conf@gmail.com.
Top

3-3-2(2023-01-04) SIVA workshop @ Waikoloa Beach Marriott Resort, Hawaii, USA.

CALL FOR PAPERS: SIVA'23
Workshop on Socially Interactive Human-like Virtual Agents
From expressive and context-aware multimodal generation of digital humans to understanding the social cognition of real humans

Submission (to be openened July, 22 2022):  https://cmt3.research.microsoft.com/SIVA2023
SIVA'23 workshop: January, 4 or 5 2023, Waikoloa, Hawaii, https://www.stms-lab.fr/agenda/siva/detail/
FG 2023 conference: January 4-8 2023, Waikoloa, Hawaii, https://fg2023.ieee-biometrics.org/

OVERVIEW

Due to the rapid growth of virtual, augmented, and hybrid reality together with spectacular advances in artificial intelligence, the ultra-realistic generation and animation of digital humans with human-like behaviors is becoming a massive topic of interest. This complex endeavor requires modeling several elements of human behavior including the natural coordination of multimodal behaviors including text, speech, face, and body, plus the contextualization of behavior in response to interlocutors of different cultures and motivations. Thus, challenges in this topic are two folds—the generation and animation of coherent multimodal behaviors, and modeling the expressivity and contextualization of the virtual agent with respect to human behavior, plus understanding and modeling virtual agent behavior adaptation to increase human’s engagement. The aim of this workshop is to connect traditionally distinct communities (e.g., speech, vision, cognitive neurosciences, social psychology) to elaborate and discuss the future of human interaction with human-like virtual agents. We expect contributions from the fields of signal processing, speech and vision, machine learning and artificial intelligence, perceptual studies, and cognitive and neuroscience. Topics will range from multimodal generative modeling of virtual agent behaviors, and speech-to-face and posture 2D and 3D animation, to original research topics including style, expressivity, and context-aware animation of virtual agents. Moreover, the availability of controllable real-time virtual agent models can be used as state-of-the-art experimental stimuli and confederates to design novel, groundbreaking experiments to advance understanding of social cognition in humans. Finally, these virtual humans can be used to create virtual environments for medical purposes including rehabilitation and training.

SCOPE

Topics of interest include but are not limited to:

+ Analysis of Multimodal Human-like Behavior
- Analyzing and understanding of human multimodal behavior (speech, gesture, face)
- Creating datasets for the study and modeling of human multimodal behavior
- Coordination and synchronization of human multimodal behavior
- Analysis of style and expressivity in human multimodal behavior
- Cultural variability of social multimodal behavior

+ Modeling and Generation of Multimodal Human-like Behavior
- Multimodal generation of human-like behavior (speech, gesture, face)
- Face and gesture generation driven by text and speech
- Context-aware generation of multimodal human-like behavior
- Modeling of style and expressivity for the generation of multimodal behavior
- Modeling paralinguistic cues for multimodal behavior generation
- Few-shots or zero-shot transfer of style and expressivity
- Slightly-supervised adaptation of multimodal behavior to context

+ Psychology and Cognition of of Multimodal Human-like Behavior
- Cognition of deep fakes and ultra-realistic digital manipulation of human-like behavior
- Social agents/robots as tools for capturing, measuring and understanding multimodal behavior (speech, gesture, face)
- Neuroscience and social cognition of real humans using virtual agents and physical robots

IMPORTANT DATES

Submission Deadline September, 12 2022 
Notification of Acceptance: October, 15 2022 
Camera-ready deadline: October, 31 2022
Workshop: January, 4 or 5 2023

VENUE

The SIVA workshop is organized as a satellite workshop of the IEEE International Conference on Automatic Face and Gesture Recognition 2023. The workshop will be collocated with the FG 2023 and WACV 2023 conferences at the Waikoloa Beach Marriott Resort, Hawaii, USA.

ADDITIONAL INFORMATION AND SUBMISSION DETAILS

Submissions must be original and not published or submitted elsewhere.  Short papers of 3 pages excluding references encourage submissions of early research in original emerging fields. Long paper of 6 to 8 pages excluding references promote the presentation of strongly original contributions, positional or survey papers. The manuscript should be formatted according to the Word or Latex template provided on the workshop website.  All submissions will be reviewed by 3 reviewers. The reviewing process will be single-blinded. Authors will be asked to disclose possible conflict of interests, such as cooperation in the previous two years. Moreover, care will be taken to avoid reviewers from the same institution as the authors.  Authors should submit their articles in a single pdf file in the submission website - no later than September, 12 2022. Notification of acceptance will be sent by October, 15 2022, and the camera-ready version of the papers revised according to the reviewers comments should be submitted by October, 31 2022. Accepted papers will be published in the proceedings of the FG'2023 conference. More information can be found on the SIVA website.

DIVERSITY, EQUALITY, AND INCLUSION

The format of this workshop will be hybrid online and onsite. This format proposes format of scientific exchanges in order to satisfy travel restrictions and COVID sanitary precautions, to promote inclusion in the research community (travel costs are high, online presentations will encourage research contributions from geographical regions which would normally be excluded), and to consider ecological issues (e.g., CO2 footprint). The organizing committee is committed to paying attention to equality, diversity, and inclusivity in consideration of invited speakers. This effort starts from the organizing committee and the invited speakers to the program committee.


ORGANIZING COMMITTEE
🌸 Nicolas Obin, STMS Lab (Ircam, CNRS, Sorbonne Université, ministère de la Culture)
🌸 Ryo Ishii, NTT Human Informatics Laboratories
🌸 Rachael E. Jack, University of Glasgow
🌸 Louis-Philippe Morency, Carnegie Mellon University
🌸 Catherine Pelachaud, CNRS - ISIR, Sorbonne UniversitéCALL FOR PAPERS: SIVA'23
Workshop on Socially Interactive Human-like Virtual Agents
From expressive and context-aware multimodal generation of digital humans to understanding the social cognition of real humans

Submission (to be openened July, 22 2022):  https://cmt3.research.microsoft.com/SIVA2023
SIVA'23 workshop: January, 4 or 5 2023, Waikoloa, Hawaii, https://www.stms-lab.fr/agenda/siva/detail/
FG 2023 conference: January 4-8 2023, Waikoloa, Hawaii, https://fg2023.ieee-biometrics.org/

OVERVIEW

Due to the rapid growth of virtual, augmented, and hybrid reality together with spectacular advances in artificial intelligence, the ultra-realistic generation and animation of digital humans with human-like behaviors is becoming a massive topic of interest. This complex endeavor requires modeling several elements of human behavior including the natural coordination of multimodal behaviors including text, speech, face, and body, plus the contextualization of behavior in response to interlocutors of different cultures and motivations. Thus, challenges in this topic are two folds—the generation and animation of coherent multimodal behaviors, and modeling the expressivity and contextualization of the virtual agent with respect to human behavior, plus understanding and modeling virtual agent behavior adaptation to increase human’s engagement. The aim of this workshop is to connect traditionally distinct communities (e.g., speech, vision, cognitive neurosciences, social psychology) to elaborate and discuss the future of human interaction with human-like virtual agents. We expect contributions from the fields of signal processing, speech and vision, machine learning and artificial intelligence, perceptual studies, and cognitive and neuroscience. Topics will range from multimodal generative modeling of virtual agent behaviors, and speech-to-face and posture 2D and 3D animation, to original research topics including style, expressivity, and context-aware animation of virtual agents. Moreover, the availability of controllable real-time virtual agent models can be used as state-of-the-art experimental stimuli and confederates to design novel, groundbreaking experiments to advance understanding of social cognition in humans. Finally, these virtual humans can be used to create virtual environments for medical purposes including rehabilitation and training.

SCOPE

Topics of interest include but are not limited to:

+ Analysis of Multimodal Human-like Behavior
- Analyzing and understanding of human multimodal behavior (speech, gesture, face)
- Creating datasets for the study and modeling of human multimodal behavior
- Coordination and synchronization of human multimodal behavior
- Analysis of style and expressivity in human multimodal behavior
- Cultural variability of social multimodal behavior

+ Modeling and Generation of Multimodal Human-like Behavior
- Multimodal generation of human-like behavior (speech, gesture, face)
- Face and gesture generation driven by text and speech
- Context-aware generation of multimodal human-like behavior
- Modeling of style and expressivity for the generation of multimodal behavior
- Modeling paralinguistic cues for multimodal behavior generation
- Few-shots or zero-shot transfer of style and expressivity
- Slightly-supervised adaptation of multimodal behavior to context

+ Psychology and Cognition of of Multimodal Human-like Behavior
- Cognition of deep fakes and ultra-realistic digital manipulation of human-like behavior
- Social agents/robots as tools for capturing, measuring and understanding multimodal behavior (speech, gesture, face)
- Neuroscience and social cognition of real humans using virtual agents and physical robots

IMPORTANT DATES

Submission Deadline September, 12 2022 
Notification of Acceptance: October, 15 2022 
Camera-ready deadline: October, 31 2022
Workshop: January, 4 or 5 2023

VENUE

The SIVA workshop is organized as a satellite workshop of the IEEE International Conference on Automatic Face and Gesture Recognition 2023. The workshop will be collocated with the FG 2023 and WACV 2023 conferences at the Waikoloa Beach Marriott Resort, Hawaii, USA.

ADDITIONAL INFORMATION AND SUBMISSION DETAILS

Submissions must be original and not published or submitted elsewhere.  Short papers of 3 pages excluding references encourage submissions of early research in original emerging fields. Long paper of 6 to 8 pages excluding references promote the presentation of strongly original contributions, positional or survey papers. The manuscript should be formatted according to the Word or Latex template provided on the workshop website.  All submissions will be reviewed by 3 reviewers. The reviewing process will be single-blinded. Authors will be asked to disclose possible conflict of interests, such as cooperation in the previous two years. Moreover, care will be taken to avoid reviewers from the same institution as the authors.  Authors should submit their articles in a single pdf file in the submission website - no later than September, 12 2022. Notification of acceptance will be sent by October, 15 2022, and the camera-ready version of the papers revised according to the reviewers comments should be submitted by October, 31 2022. Accepted papers will be published in the proceedings of the FG'2023 conference. More information can be found on the SIVA website.

DIVERSITY, EQUALITY, AND INCLUSION

The format of this workshop will be hybrid online and onsite. This format proposes format of scientific exchanges in order to satisfy travel restrictions and COVID sanitary precautions, to promote inclusion in the research community (travel costs are high, online presentations will encourage research contributions from geographical regions which would normally be excluded), and to consider ecological issues (e.g., CO2 footprint). The organizing committee is committed to paying attention to equality, diversity, and inclusivity in consideration of invited speakers. This effort starts from the organizing committee and the invited speakers to the program committee.


ORGANIZING COMMITTEE
🌸 Nicolas Obin, STMS Lab (Ircam, CNRS, Sorbonne Université, ministère de la Culture)52023-01)04)
🌸 Ryo Ishii, NTT Human Informatics Laboratories
🌸 Rachael E. Jack, University of Glasgow
🌸 Louis-Philippe Morency, Carnegie Mellon University
🌸 Catherine Pelachaud, CNRS - ISIR, Sorbonne Université

Top

3-3-3(2023-01-04) Workshop on Socially Interactive Human-like Virtual Agents (SIVA'23), Waikoloa, Hawaii
CALL FOR PAPERS: SIVA'23
Workshop on Socially Interactive Human-like Virtual Agents
From expressive and context-aware multimodal generation of digital humans to understanding the social cognition of real humans

Submission (to be openened July, 22 2022):  https://cmt3.research.microsoft.com/SIVA2023
SIVA'23 workshop: January, 4 or 5 2023, Waikoloa, Hawaii, https://www.stms-lab.fr/agenda/siva/detail/
FG 2023 conference: January 4-8 2023, Waikoloa, Hawaii, https://fg2023.ieee-biometrics.org/

OVERVIEW

Due to the rapid growth of virtual, augmented, and hybrid reality together with spectacular advances in artificial intelligence, the ultra-realistic generation and animation of digital humans with human-like behaviors is becoming a massive topic of interest. This complex endeavor requires modeling several elements of human behavior including the natural coordination of multimodal behaviors including text, speech, face, and body, plus the contextualization of behavior in response to interlocutors of different cultures and motivations. Thus, challenges in this topic are two folds—the generation and animation of coherent multimodal behaviors, and modeling the expressivity and contextualization of the virtual agent with respect to human behavior, plus understanding and modeling virtual agent behavior adaptation to increase human’s engagement. The aim of this workshop is to connect traditionally distinct communities (e.g., speech, vision, cognitive neurosciences, social psychology) to elaborate and discuss the future of human interaction with human-like virtual agents. We expect contributions from the fields of signal processing, speech and vision, machine learning and artificial intelligence, perceptual studies, and cognitive and neuroscience. Topics will range from multimodal generative modeling of virtual agent behaviors, and speech-to-face and posture 2D and 3D animation, to original research topics including style, expressivity, and context-aware animation of virtual agents. Moreover, the availability of controllable real-time virtual agent models can be used as state-of-the-art experimental stimuli and confederates to design novel, groundbreaking experiments to advance understanding of social cognition in humans. Finally, these virtual humans can be used to create virtual environments for medical purposes including rehabilitation and training.

SCOPE

Topics of interest include but are not limited to:

+ Analysis of Multimodal Human-like Behavior
- Analyzing and understanding of human multimodal behavior (speech, gesture, face)
- Creating datasets for the study and modeling of human multimodal behavior
- Coordination and synchronization of human multimodal behavior
- Analysis of style and expressivity in human multimodal behavior
- Cultural variability of social multimodal behavior

+ Modeling and Generation of Multimodal Human-like Behavior
- Multimodal generation of human-like behavior (speech, gesture, face)
- Face and gesture generation driven by text and speech
- Context-aware generation of multimodal human-like behavior
- Modeling of style and expressivity for the generation of multimodal behavior
- Modeling paralinguistic cues for multimodal behavior generation
- Few-shots or zero-shot transfer of style and expressivity
- Slightly-supervised adaptation of multimodal behavior to context

+ Psychology and Cognition of of Multimodal Human-like Behavior
- Cognition of deep fakes and ultra-realistic digital manipulation of human-like behavior
- Social agents/robots as tools for capturing, measuring and understanding multimodal behavior (speech, gesture, face)
- Neuroscience and social cognition of real humans using virtual agents and physical robots

IMPORTANT DATES

Submission Deadline September, 12 2022 
Notification of Acceptance: October, 15 2022 
Camera-ready deadline: October, 31 2022
Workshop: January, 4 or 5 2023

VENUE

The SIVA workshop is organized as a satellite workshop of the IEEE International Conference on Automatic Face and Gesture Recognition 2023. The workshop will be collocated with the FG 2023 and WACV 2023 conferences at the Waikoloa Beach Marriott Resort, Hawaii, USA.

ADDITIONAL INFORMATION AND SUBMISSION DETAILS

Submissions must be original and not published or submitted elsewhere.  Short papers of 3 pages excluding references encourage submissions of early research in original emerging fields. Long paper of 6 to 8 pages excluding references promote the presentation of strongly original contributions, positional or survey papers. The manuscript should be formatted according to the Word or Latex template provided on the workshop website.  All submissions will be reviewed by 3 reviewers. The reviewing process will be single-blinded. Authors will be asked to disclose possible conflict of interests, such as cooperation in the previous two years. Moreover, care will be taken to avoid reviewers from the same institution as the authors.  Authors should submit their articles in a single pdf file in the submission website - no later than September, 12 2022. Notification of acceptance will be sent by October, 15 2022, and the camera-ready version of the papers revised according to the reviewers comments should be submitted by October, 31 2022. Accepted papers will be published in the proceedings of the FG'2023 conference. More information can be found on the SIVA website.

DIVERSITY, EQUALITY, AND INCLUSION

The format of this workshop will be hybrid online and onsite. This format proposes format of scientific exchanges in order to satisfy travel restrictions and COVID sanitary precautions, to promote inclusion in the research community (travel costs are high, online presentations will encourage research contributions from geographical regions which would normally be excluded), and to consider ecological issues (e.g., CO2 footprint). The organizing committee is committed to paying attention to equality, diversity, and inclusivity in consideration of invited speakers. This effort starts from the organizing committee and the invited speakers to the program committee.


ORGANIZING COMMITTEE
🌸 Nicolas Obin, STMS Lab (Ircam, CNRS, Sorbonne Université, ministère de la Culture)
🌸 Ryo Ishii, NTT Human Informatics Laboratories
🌸 Rachael E. Jack, University of Glasgow
🌸 Louis-Philippe Morency, Carnegie Mellon University
🌸 Catherine Pelachaud, CNRS - ISIR, Sorbonne Université
Top

3-3-4(2023-01-16) Advanced Language Processing School (ALPS), Grenoble, France
SECOND CALL FOR PARTICIPATION
Advanced Language Processing School (ALPS)
January, 16-20 2023
Virtual Event
 
We are opening the registration for the third Advanced Language Processing School (ALPS), co-organized by University Grenoble Alpes and Naver Labs Europe.
 
*Target Audience*
 
This is a winter school covering advanced topics in NLP, and we are primarily targeting doctoral students and advanced (research) masters. A few slots will also be reserved for academics and persons working in research-heavy positions in industry.
 
*Characteristics*
 
Advanced lectures by first class researchers. A (virtual) atmosphere that fosters connections and interaction. A poster session for attendees to present their work, gather feedback and brainstorm future work ideas.
 
*Speakers*
 
The current list of speakers is: Michael Auli (Meta, USA), Kyunghyun Cho (New York University, USA); Yejin Choi (University of Washington and Allen Institute for AI, USA); Dirk Hovy (Bocconi University, Italia); Colin Raffel (University of North Carolina at Chapel Hill, Hugging Face, USA); Lucia Specia (Imperial College, UK), François Yvon (LISN/CNRS, France).  
 
*Application*
 
To apply to this winter school, please follow the instructions at http://alps.imag.fr/index.php/application/ . The deadline for applying is Sept 30th, and we will notify acceptance on October 3rd.
 
*Contact*
 
E-mail: alps@univ-grenoble-alpes.fr
Top

3-3-5(2023-04-02) Sixth International Workshop on Narrative Extraction from Texts (Text2Story'23) , Dublin, Ireland

++ CALL FOR PAPERS ++ 

 

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

Sixth International Workshop on Narrative Extraction from Texts (Text2Story'23) 

 

Held in conjunction with the 45th European Conference on Information Retrieval (ECIR'23) 

 

April 2nd, 2023 - Dublin, Ireland 

 

Website: https://text2story23.inesctec.pt

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

++ Important Dates ++ 

    - Submission deadline: January 23rd, 2023 

    - Acceptance Notification Date: March 3rd, 2023 

    - Camera-ready copies: March 17th, 2023 

    - Workshop: April 2nd, 2023 

 

++ Overview ++ 

Recent years have shown a stream of continuously evolving information making it unmanageable and time-consuming for an interested reader to track and process and to keep up with all the essential information and the various aspects of a story. Automated narrative extraction from text offers a compelling approach to this problem. It involves identifying the sub-set of interconnected raw documents, extracting the critical narrative story elements, and representing them in an adequate final form (e.g., timelines) that conveys the key points of the story in an easy-to-understand format. Although, information extraction and natural language processing have made significant progress towards an automatic interpretation of texts, the problem of automated identification and analysis of the different elements of a narrative present in a document (set) still presents significant unsolved challenges

 

++ List of Topics ++ 

In the sixth edition of the Text2Story workshop, we aim to bring to the forefront the challenges involved in understanding the structure of narratives and in incorporating their representation in well-established models, as well as in modern architectures (e.g., transformers) which are now common and form the backbone of almost every IR and NLP application. It is hoped that the workshop will provide a common forum to consolidate the multi-disciplinary efforts and foster discussions to identify the wide-ranging issues related to the narrative extraction task. To this regard, we encourage the submission of high-quality and original submissions covering the following topics: 

  •     Narrative Representation Models
  •     Story Evolution and Shift Detection
  •     Temporal Relation Identification
  •     Temporal Reasoning and Ordering of Events
  •     Causal Relation Extraction and Arrangement
  •     Narrative Summarization
  •     Multi-modal Summarization
  •     Automatic Timeline Generation
  •     Storyline Visualization
  •     Comprehension of Generated Narratives and Timelines
  •     Big Data Applied to Narrative Extraction
  •     Personalization and Recommendation of Narratives
  •     User Profiling and User Behavior Modeling
  •     Sentiment and Opinion Detection in Texts
  •     Argumentation Analysis
  •     Bias Detection and Removal in Generated Stories
  •     Ethical and Fair Narrative Generation
  •     Misinformation and Fact Checking
  •     Bots Influence
  •     Narrative-focused Search in Text Collections
  •     Event and Entity importance Estimation in Narratives
  •     Multilinguality: Multilingual and Cross-lingual Narrative Analysis
  •     Evaluation Methodologies for Narrative Extraction
  •     Resources and Dataset Showcase
  •     Dataset Annotation for Narrative Generation/Analysis
  •     Applications in Social Media (e.g. narrative generation during a natural disaster)
  •     Language Models and Transfer Learning in Narrative Analysis
  •     Narrative Analysis in Low-resource Languages

++ Dataset ++

    We challenge the interested researchers to consider submitting a paper that makes use of the tls-covid19 dataset (published at ECIR'21) under the scope and purposes of the text2story workshop. tls-covid19 consists of a number of curated topics related to the Covid-19 outbreak, with associated news articles from Portuguese and English news outlets and their respective reference timelines as gold-standard. While it was designed to support timeline summarization research tasks it can also be used for other tasks including the study of news coverage about the COVID-19 pandemic. A script to reconstruct and expand the dataset is available at https://github.com/LIAAD/tls-covid19. The article itself is available at this link: https://link.springer.com/chapter/10.1007/978-3-030-72113-8_33 

 

++ Submission Guidelines ++ 

 

    We invite two kinds of submissions: 

  • Full papers (up to 7 pages + references): Original and high-quality unpublished contributions on the theory and practical aspects of the narrative extraction task. Full-papers should introduce existing approaches, describe the methodology and the experiments conducted in detail. Negative result papers to highlight tested hypotheses that did not get the expected outcome are also welcomed.
  • Work in progressdemos and dissemination papers (up to 4 pages + references): unpublished short papers describing work in progress; demo and resource papers presenting research/industrial prototypes, datasets or software packages; position papers introducing a new point of view, a research vision or a reasoned opinion on the workshop topics; and dissemination papers describing project ideas, ongoing research lines, case studies or summarized versions of previously published papers in high-quality conferences/journals that is worthwhile sharing with the Text2Story community, but where novelty is not a fundamental issue.

    Submissions will be peer-reviewed by at least two members of the programme committee. The accepted papers will appear in the proceedings published at CEUR workshop proceedings (indexed in Scopus and DBLP) as long as they don't conflict with previous publication rights.

 

++ Workshop Format ++ 

    Participants of accepted papers will be given 15 minutes for oral presentations.

 

++ Organizing committee ++ 

    Ricardo Campos (INESC TEC; Ci2 - Smart Cities Research Center, Polytechnic Institute of Tomar, Tomar, Portugal)

    Alípio M. Jorge (INESC TEC; University of Porto, Portugal)

    Adam Jatowt (University of Innsbruck, Austria)

    Sumit Bhatia (Media and Data Science Research Lab, Adobe)

    Marina Litvak (Shamoon Academic College of Engineering, Israel)

 

++ Proceedings Chair ++

    João Paulo Cordeiro (INESC TEC & Universidade da Beira do Interior)

    Conceição Rocha (INESC TEC) 

 

++ Web and Dissemination Chair ++

    Hugo Sousa (INESC TEC & University of Porto) 

    Behrooz Mansouri (Rochester Institute of Technology)

 

++ Program Committee ++

    Álvaro Figueira (INESC TEC & University of Porto)

    Andreas Spitz (University of Konstanz)

    Antoine Doucet (Université de La Rochelle)

    António Horta Branco (University of Lisbon)

    Arian Pasquali (CitizenLab)

    Bart Gajderowicz (University of Toronto)

    Brenda Santana (Federal University of Rio Grande do Sul)

    Bruno Martins (IST & INESC-ID, University of Lisbon)

    Daniel Loureiro (Cardiff University)

    Dennis Aumiller (Heidelberg University)

    Dhruv Gupta (Norwegian University of Science and Technology)

    Dyaa Albakour (Signal UK)

    Evelin Amorim (INESC TEC)

    Henrique Cardoso (INESC TEC & University of Porto)

    Ismail Altingovde (Middle East Technical University)

    João Paulo Cordeiro (INESC TEC & University of Beira Interior)

    Kiran Bandeli (Walmart Inc.)

    Luca Cagliero (Politecnico di Torino)

    Ludovic Moncla (INSA Lyon)

    Marc Finlayson (Florida International University)

    Marc Spaniol (Université de Caen Normandie)

    Moreno La Quatra (Politecnico di Torino)

    Nuno Guimarães (INESC TEC & University of Porto)

    Pablo Gamallo (University of Santiago de Compostela)

    Pablo Gervás (Universidad Complutense de Madrid)

    Paulo Quaresma (Universidade de Évora)

    Paul Rayson (Lancaster University)

    Ross Purves (University of Zurich)

    Satya Almasian (Heidelberg University)

    Sérgio Nunes (INESC TEC & University of Porto)

    Simra Shahid (Adobe's Media and Data Science Research Lab)

    Udo Kruschwitz (University of Regensburg) 

 

++ Contacts ++ 

    Website: https://text2story23.inesctec.pt 

    For general inquiries regarding the workshop, reach the organizers at: text2story2023@easychair.org

Top

3-3-6(2023-05-26) HISPhonCog 2023: Hanyang International Symposium on Phonetics and Cognitive Sciences of Language 2023, Hanyang University, Seoul, South Korea

Dear colleagues and prospective participants of HISPhonCog 2023

(my apologies for cross listings). 

We are very pleased to inform you that we will resume our annual HISPhonCog conference in 2023 after such a long pause due to Covid 19.
We sincerely hope that we will be able to meet many of you in person in Seoul in May 2023.
Best wishes,
Taehong Cho
Chair

 

HISPhonCog 2023: Hanyang International Symposium on Phonetics and Cognitive Sciences of Language 2023

Hanyang University, Seoul, South Korea, May 26-27, 2023

https://site.hanyang.ac.kr/web/hisphoncog/about-hisphoncog/2023

HIPCS (Hanyang Institute for Phonetics and Cognitive Sciences of Language) at Hanyang University, together with Department of English Language and Literature, holds its 3rd annual international symposium on current issues on phonetics and cognitive sciences of language (HISPhonCog) 2023 on 26-27 May, 2023.

Theme for HISPhonCog 2023

Linguistic and cognitive functions of fine phonetic detail underlying sound systems and/or sound change

We have witnessed over past decades that the severance between phonetics and phonology has been steadily eroding along with the awareness of the importance of scalar and gradient aspects of speech in understanding the linguistic sound system and sound change. In particular, non-contrastive phonetic events (either at the subphonemic level or at the suprasegmental level of micro-prosody), which had traditionally been understood to be beyond the speaker’s control (as low-level automatic physiological phenomena), have been reinterpreted as part of the grammar. They have turned out to be either systematically linked with phonological contrasts in the segmental or intonational phonology and higher-order linguistic structures (e.g., prosodic structure, morphosyntactic structure, information structure) or governed by language-specific phonetic rules that make the seemingly cross-linguistically similar phonetic processes distinctive, both of which may in turn serve as driving forces for sound change. Furthermore, we have enjoyed seeing that the investigation of linguistic roles of fine phonetic detail provides insights into phonetic underpinnings of other speech variation phenomena such as sociolinguistically-driven speech variation and effects of native-language experience on production and perception of unfamiliar languages or L2. Most remarkably, such phonetic underpinnings are not purely segmental in nature, but they are suprasegmental or systematically related to prosodic structure and the intonational grammar of the language.  

We invite submissions which provide some empirical (experimental) evidence for exploring any issues related to the theme of the symposium. We also wish to have a special session on Articulatory Phonology and speech dynamics bearing on the issue of how gradient and categorical aspects of human speech may be combined to serve as a cognitive linguistic unit. We will also consider submissions that deal with other general issues in speech production and perception in L1 and L2. We particularly welcome submissions from the neuro-cognitive perspectives or from the phonetics-prosody interplay.  

Invited speakers

  • Adam Albright (MIT)
  • Lisa Davidson (New York University)
  • John Kingston (University of Massachusetts, Amherst)
  • Marianne Pouplier (University Munich)
  • Donca Steriade (MIT)
  • Andrew Wedel (University of Arizona)
  • Douglas Whalen (CUNY and Haskins Laboratories)
  • Alan Yu (University of Chicago)

A possible Special Issue to be published in a journal

  • Oral presentations (including invited talks) and a limited number of selected posters (related to the themes of the conference under the rubric of linguistic/cognitive functions of fine phonetic detail) will be invited to submit a full manuscript to be considered further for a possible inclusion in a Special Issue in a peer-reviewed international journal.
  • The actual journal has not been selected but we are considering one of the followings journals subject to final approval from a targeted journal: Journal of Phonetics, Phonetica, Journal of International Phonetic Association, Laboratory Phonology, Language and Speech, Linguistic Vanguard, The Linguistic Review, etc. 
  • Once we know the journal, we will announce it on the HISPhonCog 2023 webpage.
  • (tentative) Guest editors: T. Cho, S. Kim & H. MItterer
  • If you wish to have your paper considered for the special issue, regardless of whether your paper is selected for oral presentation or not, please indicate your intention when you submit an abstract through Easy Chair. 
  • We will also consider papers on the theme, even if they are not to be presented at the conference. In such a case, please send a two-page abstract (including figures and references within the two page limit) to Taehong Cho at tcho@hanyang.ac.kr by February 10. 
  • Deadline of submission of invited/selected papers (for a special issue): July 30, 2023. (This deadline will be strictly enforced.)
  • Note that each selected paper will undergo standard editorial/review processes which may eventually lead to its exclusion (rejection). 

Support for international participants (possible free accommodation)

  • As before, we will do our best to provide free local hotel accommodation (one room for up to 3 nights per presentation) for international presenters affiliated with a foreign institute/university, travelling from abroad.
  • Please note, however, that the local hotel we had a contract with before was closed due to Covid 19. So we may not be able to make an arrangement for free accommodation. If we don't find a solution, we will have to provide a small amount of partial accommodation subsidy with priority to be given to student presenters. The details will be sent to qualified individuals along with an acceptance letter, depending on the final budget approval.  

Free registration fees

  • We are very pleased to inform you that we will be able to make registration free as before.
  • Free registion will include free banquet, free munches for breakfast, free refreshments and a free conference handbook
  • Attendees will have to pay (optionally) for lunches (10 USD or equivalent in KRW for each lunch) at the time of arrival. (The detail will be provided along with registration.) 
  • Pre-registration should be made by no later than April 10, 2023 to be guaranteed for possible (partial) accommodation support (for international presenters) and free registration (for all foreign and domestic participants and audience).
  • A pre-registration form that arrives a few days after April 10 may still be considered for free registration, depending on the budget and availability. Please contact us at hanyang.hipcs@gmail.com if you miss the deadline by a few days but still would like to register in advance.
  • On-site registration will be possible for small fees, but with no guarantee for lunches and banquet admission.
  • For further information about how to register, please check the website later.

Abstract submission instruction

Call for Satellite Workshop 

  • We set aside May 25 (Thursday), 2023 (the day before the main conference) for one or two possible satellite workshops. 
  • We will provide rooms and light refreshments free of charge with support of our onsite personnel. 
  • If you are interested, please contact Taehong Cho directly at tcho@hanyang.ac.kr. The proposal will be welcome until the two slots are filled. 

Timeline

  • Deadline of submission of a two-page long abstract: February 10, 2023
  • Notification of Acceptance: No later than March 10, 2023
  • Free Registration with free accommodation: No later than April 10, 2023
  • Satellite Workshop (if organized): May 25, 2023
  • Symposium dates: May 26-27, 2023 
  • (Submission of invited papers to a special issue: July 30, 2023)

Local Organizing Institute and Committee

Organizing Bodies of HISPhonCog:

  • HIPCS (the Hanyang Institute for Phonetics and Cognitive Sciences of Language)
  • CRC for Articulatory DB and Cognitive Sciences
  • Department of English Language and Literature, Hanyang University

Organizing Committee:

  • Taehong Cho (Chair, HIPCS, Hanyang University)
  • Sahyang Kim (Hongik University & HIPCS)
  • Say Young Kim (HIPCS, Hanyang University, Seoul)
  • Suyeon Im (HIPCS, Hanyang University, Seoul)

  Contact

Top

3-3-7(2023-06-04) CfP ICASSP 2023, Rhodes Island, Greece

 

 

 

Announcing the ICASSP 2023 Call for Papers! 

The Call for Papers for ICASSP 2023 is now open! The 48th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) will be held from 4-9 June 2023 in Rhodes Island, Greece. 
 
The flagship conference of the IEEE Signal Processing Society will offer a comprehensive technical program presenting all the latest developments in research and technology for signal processing and its applications. Featuring world-class oral and poster sessions, keynotes, plenaries and perspective talks, exhibitions, demonstrations, tutorials, short courses, and satellite workshops, it is expected to attract leading researchers and global industry figures, providing a great networking opportunity. Moreover, exceptional papers and contributors will be selected and recognized by ICASSP.

Technical Scope

 

We invite submissions of original unpublished technical papers on topics including but not limited to:

  • Applied Signal Processing Systems
  • Audio & Acoustic Signal Processing
  • Biomedical Imaging & Signal Processing
  • Compressive Sensing, Sparse Modeling
  • Computational Imaging
  • Computer Vision 
  • Deep Learning/Machine Learning for Signal Processing 
  • Image, Video & Multidimensional Signal Processing 
  • Industrial Signal Processing 
  • Information Forensics & Security 
  • Internet of Things
  • Multimedia Signal Processing
  • Quantum Signal Processing
  • Remote Sensing & Signal Processing
  • Sensor Array & Mulltichanel SP
  • Signal Processing for Big Data
  • Signal Processing for Communication
  • Signal Processing for Cyber Security
  • Signal Processing for Education
  • Signal Processing for Robotics
  • Signal Processing Over Graphs
  • Signal Processing Theory & Methods 
  • Speech & Language Processing

SP Society Journal Paper Presentations

Authors of papers published or accepted in IEEE SPS journals may present their work at ICASSP 2023 at appropriate tracks. These papers will neither be reviewed nor included in the proceedings. In addition, the IEEE Open Journal of Signal Processing (OJSP) will provide a special track for longer submissions with the same processing timeline as ICASSP. Accepted papers will be published in OJSP and presented in the conference but will not be included in the conference proceedings.

 

Open Preview

Conference proceedings will be available in IEEE Xplore, free of charge, to all customers, 30 days prior to the conference start date, through the conference end date.

 

Important Dates

  • Paper Submission Deadline: 19 October 2022
  • Paper Acceptance Notification: 8 February 2023 
  • SPS Journal Papers/Letters Deadline: 8 February 2023
  • Camera Ready Paper Deadline: 6 March 2023 
  • Author Registration Deadline: 20 March 2023 
  • Open Preview Starts: 5 May 2023
Top

3-3-8(2023-06-04) CfP Student competition at ICASSP 2023, Rhodes, Greece
 
Call for Proposals
Student Competitions at IEEE ICASSP 2023
The IEEE Signal Processing Society is calling those interested in organizing one of the student competitions that will be held at ICASSP 2023! The SP Cup gives SPS Students the opportunity to solve real-life problems using signal processing or video and image processing methods. Rounds of open competition are held before three final teams are selected to present their work and compete for the US$5,000 grand prize at ICASSP 2023! See the full SP Cup Call for Proposals.
 
The 5-MICC is the Society’s new video contest in which teams of students create five-minute videos that highlight and generate excitement about signal processing concepts. The final three teams’ videos will be selected and featured on the ICASSP website, where the ICASSP and signal processing community can vote for their favorites! Those teams will be invited to attend ICASSP for the final phase of the competition and US$5,000 grand prize. See the full 5-MICC Call for Proposals.
 
If you are interested in submitting a proposal for the SP Cup or the 5-Minute Video Clip Contest being held at ICASSP 2023, please submit your proposal for endorsement to the SPS Technical Committee (TC) that best fits your proposal by 6 January 2023 for the SP Cup and 3 January 2023 for the 5-MICC. Your proposal must be endorsed by one of the TCs. You can find the Society’s TCs located on the Technical Committees page on the SPS website. The endorsed proposals will then be submitted by the TC Chairs to SP-SC-STUDENTSERVICES@LISTSERV.IEEE.ORG by 13 January 2023 for the SP Cup and 7 January 2023 for the 5-MICC.

If you have questions, you can reach out directly to Angshul Majumdar, SPS Student Services Director, and Jaqueline Rash, SPS Membership Program and Events Administrator, or the SSC alias.
Top

3-3-9(2023-06-04) CfSatellite Workshops ICASSP 2023, Rhodes Island, Greece

 

 Call for Satellite Workshops at ICASSP 2023

The organizing committee of ICASSP 2023 invites proposals for Satellite Workshops, aiming to inaugurate such tradition with the goals of enriching the conference program, attracting a wider audience, and enhancing inclusivity for students and professionals.
 
The ICASSP Satellite Workshops will be half or full-day events and will take place the day before or after the main conference technical program at the conference venue. The workshops may include a mix of regular papers, invited presentations, keynotes, and panels, encouraging the participation of attendees in active discussions.
 
Submit your proposals by 9 November 2022. 

Workshop Logistics

 

Organizers of ICASSP 2023 Satellite Workshops will be responsible for the workshop scientific planning and promotion, including the setup of their external website (this will be linked from the main ICASSP 2023 site but not hosted there), running of the paper reviewing process, undertaking all communication with the submitted paper authors, creating and announcing the event schedule, abiding by the Important Dates listed below, and seamlessly communicating with the Workshop Chairs.

 

Please note that specifically for workshops that will appear at IEEE Xplore, the paper submission and reviewing process will be conducted through the ICASSP 2023 paper management system (Microsoft CMT).

 

The ICASSP 2023 organizers will handle workshop registration, allocation of facilities, and distribution of the workshop papers in electronic format. Workshop attendance will be free-of-charge for the main conference registrants, while a reduced registration fee will be charged to workshop-only attendees.

Important Dates

  • Workshop Proposal Submission Deadline: 9 November 2022

  • Workshop Proposal Acceptance Notification: 23 November 2022

  • Workshop Website Online: 7 December 2022

  • Workshop Paper Submission Deadline: 15 February 2023

  • Workshop Paper Acceptance Notification: 14 April 2023

  • Workshop Camera Ready Paper Deadline: 28 April 2023

Top

3-3-10(2023-06-12)) 13th International Conference on Multimedia Retrieval, Thessaloniki, Greece

ICMR2023 – ACM International Conference on Multimedia Retrieval

Top

3-3-11(2023-06-15) JPC 2023 (Journées de phonétique clinique)- Toulouse, France

JPC 2023 - Toulouse du 15 au 17 juin 2023

https://www.irit.fr/jpc2023/


2e Appel à Communication

Depuis leur création en 2005, les Journées de Phonétique Clinique (JPC) ont été régulièrement organisées sur une base bisannuelle. Après une dernière édition organisée en Belgique par nos collègues du Laboratoire de phonétique de l’Université de Mons en 2019 (sous l’égide de l’Institut de Recherche en Sciences et Technologies du Langage), les JPC reviennent en France en 2023 (après annulation en 2021) pour leur 9e édition. Co-organisée par l’Institut de Recherche en Informatique de Toulouse (IRIT), le laboratoire de Neuro-Psycho-Linguistique (LNPL) et le Centre Hospitalo-Universitaire de Toulouse ainsi que par le Laboratoire Informatique d’Avignon (LIA), la manifestation se tiendra à l’Université de Toulouse du 15 au 17 juin 2023.

Rencontre scientifique internationale, les Journées de Phonétique Clinique sont principalement destinées à rassembler et à favoriser les échanges entre chercheurs, cliniciens, informaticiens, ingénieurs, phonéticiens et tout autre professionnel s’intéressant au fonctionnement de la parole, de la voix et du langage. Les JPC accueillent autant les experts que les jeunes chercheurs et les étudiants des domaines cliniques (médecine, orthophonie/logopédie), psychologique, informatique et des sciences du langage.

La production et la perception de la parole, de la voix et du langage de l’enfant et de l’adulte, sain ou atteint d’une pathologie, sont les domaines de prédilection des JPC. Ils y sont ainsi abordés selon des points de vue variés, permettant le partage des savoirs et l’ouverture de nouvelles pistes de réflexion, de recherche et de collaboration.

Lors de cette neuvième édition, la thématique des mesures de la parole sera mise en avant. Elle s’inscrit dans un cadre conceptuel dont les facettes sont multiples : analyses perceptives, traitement automatique du signal, caractérisations de l’intelligibilité, du trouble de la parole, des di/ysfluences atteignant le débit de la parole, la prosodie… Sa pertinence clinique est essentielle : l’évaluation du trouble, de ses conséquences fonctionnelles et de l’impact sur la qualité de vie est primordiale pour le suivi des patients atteints de pathologies neurologiques, cancérologiques…

Trois conférences plénières seront prévues autour du thème des journées. Une table ronde ainsi que des ateliers feront également partie du programme de cette nouvelle édition. 

Les propositions de communication (résumé de 400 mots, hors titre, auteurs et références) porteront sur les problématiques suivantes (liste non exhaustive) :

  • Parole et perturbations des systèmes perceptifs, auditifs et visuels
  • Modélisation de la parole et de la voix pathologiques
  • Perturbations du système oro-pharyngo-laryngé
  • Évaluation fonctionnelle de la parole, du langage et de la voix.
  • Diagnostic et traitement des troubles de la parole et de la voix parlée et chantée
  • Instrumentation et ressources en phonétique clinique
  • Troubles cognitifs et moteurs de la parole et du langage

Une attention particulière sera portée aux propositions ciblant la thématique autour des mesures de la parole.                                       

Dates importantes : 

- 20 janvier 2023 → Date limite de soumission des résumés via SciencesConf : https://jpc2023.sciencesconf.org/
- 30 mars 2023 → Notification aux auteurs
- du 30 mars au 15 mai 2023 → Inscriptions au tarif réduit
- 15 mai 2023 → Version finale des résumés
- Du 15 au 17 juin 2023 → Journées 

Téléchargez le flyer des JPC'2023 pour diffusion dans vos labos, sociétés savantes, ... 

Top

3-3-12(2023-07-15) MLDM 2023 : 18th International Conference on Machine Learning and Data Mining, New York,NY, USA

MLDM 2023 : 18th International Conference on Machine Learning and Data Mining
http://www.mldm.de
 
When    Jul 16, 2023 - Jul 21, 2023
Where    New York, USA
Submission Deadline    Jan 15, 2023
Notification Due    Mar 18, 2023
Final Version Due    Apr 5, 2023
Categories:    machine learning   data mining   pattern recognition   classification
 
Call For Papers
MLDM 2023
18th International Conference on Machine Learning and Data Mining
July 15 - 19, 2023, New York, USA

The Aim of the Conference
The aim of the conference is to bring together researchers from all over the world who deal with machine learning and data mining in order to discuss the recent status of the research and to direct further developments. Basic research papers as well as application papers are welcome.

Chair
Petra Perner Institute of Computer Vision and Applied Computer Sciences IBaI, Germany

Program Committee
Piotr Artiemjew University of Warmia and Mazury in Olsztyn, Poland
Sung-Hyuk Cha Pace Universtity, USA
Ming-Ching Chang University of Albany, USA
Mark J. Embrechts Rensselaer Polytechnic Institute and CardioMag Imaging, Inc, USA
Robert Haralick City University of New York, USA
Adam Krzyzak Concordia University, Canada
Chengjun Liu New Jersey Institute of Technology, USA
Krzysztof Pancerz University Rzeszow, Poland
Dan Simovici University of Massachusetts Boston, USA
Agnieszka Wosiak Lodz University of Technology, Poland
more to be annouced...


Topics of the conference

Paper submissions should be related but not limited to any of the following topics:

Association Rules
Audio Mining
Autoamtic Semantic Annotation of Media Content
Bayesian Models and Methods
Capability Indices
Case-Based Reasoning and Associative Memory
case-based reasoning and learning
Classification & Prediction
classification and interpretation of images, text, video
Classification and Model Estimation
Clustering
Cognition and Computer Vision
Conceptional Learning
conceptional learning and clustering
Content-Based Image Retrieval
Control Charts
Decision Trees
Design of Experiment
Desirabilities
Deviation and Novelty Detection
Feature Grouping, Discretization, Selection and Transformation
Feature Learning
Frequent Pattern Mining
https://www.icphs2023.org/, where it is also possible to register for email notifications concerning the congress.

 

Contact: icphs2023@guarant.cz

 

Top

3-3-14(2023-08-07) IPA bursaries for ICPhS

The president of the IPA, Michael Ashby, would like to call attention to the IPA's generous scheme of student awards and travel bursaries for ICPhS. He hopes that many of us will encourage our students to apply.

https://www.internationalphoneticassociation.org/news/202210/ipa-student-awardstravel-bursaries-and-g%C3%B6sta-bruce-scholarships-icphs-2023 <https://www.internationalphoneticassociation.org/news/202210/ipa-student-awardstravel-bursaries-and-g%C3%B6sta-bruce-scholarships-icphs-2023>

Top

3-3-15(2023-09-04) CfP 26th Intern.Conf. on text, speech and dialogue (TSD 2023), Plzen (Pilsen), Czech Republic
                     TSD 2023 - FIRST CALL FOR PAPERS
**************************************************************************

The twenty-sixth International Conference on Text, Speech and Dialogue (TSD 2023)
            Plzen (Pilsen), Czech Republic, September 4-7, 2023
                       http://www.tsdconference.org/

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

Venue: Plzen (Pilsen), Czech Republic


SUBMISSION DEADLINE

23 April 2023 ............ Deadline for submission of contributions


DATES AND FEES

Deadline for submission of contributions: 23 April 2023
Notification of acceptance or rejection:  22 May 2023
Deadline for submission of accepted camera-ready papers: 4 June 2023
TSD 2023: 4 -- 7 September 2023


TSD SERIES

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

The history of the TSD conference dates back to 1998 when the event was
held for the first time, that time as an international workshop, in Brno,
Czech Republic. The essential idea behind the project was to establish
a scientific meeting platform that would act as a bridge between the East
and the West.


TOPICS

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

Speech Recognition
- multilingual, continuous, emotional speech, handicapped speaker,
  out-of-vocabulary words, alternative way of feature extraction,
  new models for acoustic and language modelling
Corpora and Language Resources
- monolingual, multilingual, text, and spoken corpora, large web corpora,
  disambiguation, specialized lexicons, dictionaries
Speech and Spoken Language Generation
- multilingual, high fidelity speech synthesis, computer singing
Tagging, Classification and Parsing of Text and Speech
- multilingual processing, sentiment analysis, credibility analysis,
  automatic text labeling, summarization, authorship attribution
Semantic Processing of Text and Speech
- information extraction, information retrieval, data mining, semantic web,
  knowledge representation, inference, ontologies, sense disambiguation, plagiarism detection
Integrating Applications of Text and Speech Processing
- machine translation, natural language understanding, question-answering
  strategies, assistive technologies
Automatic Dialogue Systems
- self-learning, multilingual, question-answering systems, dialogue strategies,
  prosody in dialogues
Multimodal Techniques and Modelling
- video processing, facial animation, visual speech synthesis, user modelling,
  emotion and personality modelling


PROGRAMME COMMITTEE

Elmar Noth, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Germany (General Chairman)
Rodrigo Agerri, University of the Basque Country, Spain
Eneko Agirre, University of the Basque Country, Spain
Vladimir Benko, Slovak Academy of Sciences, Slovakia
Archna Bhatia, Carnegie Mellon University, United States
Jan Cernocky, Brno University of Technology, Czechia
Simon Dobrisek, University of Ljubljana, Slovenia
Kamil Ekstein, University of West Bohemia, Czechia
Karina Evgrafova, Saint-Petersburg State University, Russia
Yevhen Fedorov, Cherkasy State Technological University, Ukraine
Volker Fischer, EML Speech Technology GmbH, Germany
Darja Fiser, Institute of Contemporary History, Slovenia
Lucie Flek, Philipps-Universitat Marburg, Germany
Bjorn Gamback, Norwegian University of Science and Technology, Norway
Radovan Garabik, Slovak Academy of Sciences, Slovakia
Alexander Gelbukh, Instituto Politecnico Nacional, Mexico
Louise Guthrie, University of Texas at El Paso, United States
Tino Haderlein, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Germany
Jan Hajic, Charles University, Czechia
Eva Hajicova, Charles University, Czechia
Yannis Haralambous, IMT Atlantique, France
Hynek Hermansky, Johns Hopkins University, United States
Jaroslava Hlavacova, Charles University, Czechia
Ales Horak, Masaryk University, Czechia
Eduard  Hovy, Carnegie Mellon University, United States
Denis Jouvet, Inria, France
Maria Khokhlova, Saint Petersburg State University, Russia
Aidar Khusainov, Tatarstan Academy of Sciences, Russia
Daniil Kocharov, Saint Petersburg State University, Russia
Miloslav Konopik, University of West Bohemia, Czechia
Ivan Kopecek, Masaryk University, Czechia
Valia Kordoni, Humboldt University of Berlin, Germany
Evgeny Kotelnikov, Vyatka State University, Russia
Pavel Kral, University of West Bohemia, Czechia
Siegfried Kunzmann, Amazon Alexa Machine Learning, United States
Nikola Ljubesic, Jozef Stefan Institute, Croatia
Natalija Loukachevitch, Lomonosov Moscow State University, Russia
Bernardo Magnini , Fondazione Bruno Kessler, Italy
Oleksandr Marchenko, Taras Shevchenko National University of Kyiv, Ukraine
Vaclav Matousek, University of West Bohemia, Czechia
Roman Moucek, University of West Bohemia, Czechia
Agnieszka  Mykowiecka, Polish Academy of Sciences, Poland
Hermann Ney, RWTH Aachen University, Germany
Joakim Nivre, Uppsala University, Sweden
Juan Rafael  Orozco-Arroyave, University of Antioquia, Colombia
Karel Pala, Masaryk University, Czechia
Maciej Piasecki, Wroclaw University of Science and Technology, Poland
Josef Psutka, University of West Bohemia, Czechia
James  Pustejovsky, Brandeis University, United States
German Rigau, University of the Basque Country, Spain
Paolo Rosso, Universitat Politecnica de Valencia, Spain
Leon Rothkrantz, Delft University of Technology, Netherlands
Anna Rumshisky, University of Massachusetts Lowell, United States
Milan Rusko, Slovak Academy of Sciences, Slovakia
Pavel Rychly, Masaryk University, Czechia
Mykola Sazhok, International Research and Training Center for Information Technologies and Systems, Ukraine
Odette Scharenborg, Delft University of Technology, Netherlands
Pavel Skrelin, Saint Petersburg State University, Russia
Pavel Smrz, Brno University of Technology, Czechia
Petr Sojka, Masaryk University, Czechia
Georg Stemmer, Intel Corp., Germany
Marko Robnik Sikonja, University of Ljubljana, Slovenia
Marko Tadic, University of Zagreb, Croatia
Jan Trmal, Johns Hopkins University, Czechia
Tamas Varadi, Hungarian Academy of Sciences, Hungary
Zygmunt Vetulani, Adam Mickiewicz University, Poland
Aleksander Wawer, Polish Academy of Sciences, Poland
Pascal Wiggers, Amsterdam University of Applied Sciences, Netherlands
Marcin Wolinski, Polish Academy of Sciences, Poland
Alina Wroblewska, Polish Academy of Sciences, Poland
Victor Zakharov, Saint Petersburg State University, Russia
Jerneja Zganec Gros, Alpineon, Slovenia


FORMAT OF THE CONFERENCE

The conference program will include presentations of invited papers, oral
presentations, and poster/demonstration sessions. Papers will be presented
in plenary or topic oriented sessions.

The official language of the TSD 2023 conference is English. Thus, the
submitted papers must be written in English. However, papers dealing with
text and speech processing in linguistic environments other than English
are strongly encouraged (as long as they are written in English).

The conference is planned to be held fully on-site, a hybrid scheme (some
participants on site, some online) may come on the agenda if necessary.

Social events including an excursion to the Pilsner Urquell brewery and
a trip in the vicinity of Plzen will allow for additional informal
interactions.


SUBMISSION OF PAPERS

Authors are invited to submit a full paper not exceeding 12 pages
(including references) formatted in the LNCS style. Those accepted will be
presented either orally or as posters. The decision about the presentation
format will be based upon the recommendation of the reviewers. The authors
are asked to submit their papers using the on-line form accessible from the
conference website.

Papers submitted to TSD 2023 must not be under review by any other
conference or publication during the TSD review cycle, and must not be
previously published or accepted for publication elsewhere.

Authors are also invited to present actual projects, developed software or
interesting material relevant to the topics of the conference. The
presenters of demonstrations should provide an abstract not exceeding one
page.  The demonstration abstracts will not appear in the conference
proceedings.


IMPORTANT DATES

23 April 2023 ............ Submission of full papers for review
22 May 2023 .............. Notification of acceptance
4 June 2023 .............. Final papers (camera ready) and registration
4-7 September 2023 ....... Conference dates

The accepted conference contributions will be collected in the proceedings
published by Springer that will be made available to participants at the
time of the conference.


OFFICIAL LANGUAGE

The official language of the conference is English.


ACCOMMODATION

The organizing committee will arrange discounts on accommodation in a 4-star
hotel at the conference venue. The current prices of the accommodation will
be available at the conference website. There will be also a low-budget option
available in the students' halls of residence.


ADDRESS

All paper correspondence regarding the conference should be addressed to:

    TSD 2023 -- Dept. of Computer Science and Engineering
    Faculty of Applied Sciences, University of West Bohemia
    Univerzitni 2732/8, 301 00 Plzen, Czech Republic

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

    Ms Marluce Quaresma -- TSD 2023 Conference Secretary
    E-mail: tsd2023@tsdconference.org
    Phone: +420 730 851 103

The official TSD 2023 homepage is: http://www.tsdconference.org/


LOCATION

The city of Plzen (or Pilsen in Germanic languages) is situated in the
heart of West Bohemia at the confluence of four rivers: Uhlava, Uslava,
Radbuza, and Mze. With its approx. 171,000 inhabitants it is the fourth
largest city in the Czech Republic and an important industrial, commercial,
and administrative centre. It is also the capital of the Pilsen Region. In
addition, it has been elected the European Capital of Culture for 2015 by
the Council of the European Union.

The city of Plzen has a convenient location in the centre of West Bohemia,
close to the German border, on the confluence of four rivers. The place
lied on the crossroads of important medieval trade routes and nowadays it
naturally forms an important highway and railroad junction; thus, it is
easily accessible using both individual and public means of transport.

Plzen lies 85 km (53 mi) south-westwards from the Czech capital Prague, 222
km (138 mi) from the Bavarian capital Munich, 148 km (92 mi) from the Saxon
capital Dresden, and 174 km (108 mi) from the Upper Austrian capital Linz.

The closest international airport is the Vaclav Havel Airport Prague, which
is 75 km (47 mi) away and one can get from there to Plzen very easily
within about two hours by Prague public transport and a train/bus.
 
Top

3-3-16(2023-12-16) The 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2023), Taipeh, Taiwan

The 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2023) will be held on December 16 – 20, 2023, at Taipei, Taiwan. The workshop is held every two years and has a tradition of bringing together researchers from academia and industry in an intimate and collegial setting to discuss problems of common interest in automatic speech recognition and understanding. The conference will be an 'in-person' event (with a virtual component for those that can not attend physically). The event will be held in the Beitou Area, the town of hot springs of Taipei. We encourage all to join us for this wonderful event in Taiwan; looking forward to seeing you all in Taiwan. The paper submission deadline is July 3rd, 2023.
http://www.asru2023.org/

Top

3-3-17(2024-05-13) 13th International Seminar on Speech Production, Autrans, France
13th International Seminar on Speech Production, 13-17 May 2024, in Autrans, France
 
It is time for the next International Seminar on Speech Production.
 
After the launch in 1988 in Grenoble, followed by in Leeds (1990), Old Saybrook (1993), Autrans (1996), Kloster Seeon (2000), Sydney (2003), Ubatatuba (2006), Strasbourg (2008), Montreal (2011), Cologne (2014), Tianjin (2017) and virtually in in 2020, the 13th ISSP will come back (close) to Grenoble.
 
After a very successful virtual ISSP in 2020 (Haskins Labs), we are ready again for an in-person meeting in a very beautiful location in the mountains of Autrans (of course we will provide an option to attend virtually).
Take your calendars and mark the 13-17 May 2024 for the 13th International Seminar on Speech Production co-organized by several laboratories in France
 
More information including the website and important dates will be provided soon.
 
We are looking forward to meeting you in Autrans in 2024!
 
The organizing committee, Cécile Fougeron & Pascal Perrier together with Jalal Al-Tamimi, Pierre Baraduc, Véronique Boulanger, Mélanie Canault, Maëva Garnier, Anne Hermes, Fabrice Hirsch, Leonardo Lancia, Yves Laprie, Yohann Meynadier, Slim Ouni, Rudolph Sock, Béatrice Vaxelaire
 
Follow us on twitter @issp2024!
 

Claire PILLOT-LOISEAU

. Maître de Conférences HDR en Phonétique
. Responsable du DU de Phonétique Appliquée à la Langue Française (DUPALF)

Laboratoire de Phonétique et Phonologie UMR 7018 (LPP)
Université Sorbonne Nouvelle, département Institut de Linguistique et de Phonétique Générales et Appliquées (ILPGA)

. 4, rue des Irlandais, 75005 PARIS (Laboratoire)  
. 8, Avenue de Saint Mandé, 75012, PARIS (Université)
Top



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

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

Powered by ISCA