Le Groupe Acoustique de la Parole (GAP) de la Société Française d'Acoustique organiseune journée d’étude 'Acoustique de la voix et de la parole : modèles, mesures, maquettes', ouverte à tous sur inscription et gratuite / The Speech Acoustics Group (GAP) of  French Acoustical Society organizes a scientific day 'Acoustics of voice and speech: models, measurements, testbeds', open to all with free registration.

Retrouvez tous les détails du programme sur le site de la SFA / Find all the details of the program on the website of the SFA :
https://sfa.asso.fr/manifestations-sfa/journee-acoustique-de-la-voix-et-de-la-parole-modeles-mesures-maquettes/?preview_id=2530&preview_nonce=af4f857821&preview=true

ou sur ce lien / or on this link : https://sfa.asso.fr/wp-content/uploads/2023/02/2023-03-15-Journee-Voix-SFA-1.pdf

Pour s'inscrire, merci de remplir le formulaire ci-dessous / To register, please fill in the form below :
https://framaforms.org/inscription-a-la-journee-gap-sfa-du-mercredi-15-mars-2023-1676538860

Back

Top

++ 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 progress, demos 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

Back

Top

Call for Contributions

Special track
SATASK: Task-based evaluation of speech/audio interfaces

Chair
Prof. Gerald Penn, University of Toronto, Canada
gpenn@cs.toronto.edu

along with

ACHI 2023, The Sixteenth International Conference on Advances in
Computer-Human Interactions
https://www.iaria.org/conferences2023/ACHI23.html

April 24 - 28, 2023
Venice, Italy

Long gone is the hegemony of the Word Error Rate (WER).  After years
of painstaking research by the Human-Computer Interaction (HCI)
community documenting the enormous variance between WER and the actual
performance of speech recognition systems within the context of
applications other than transcription, speech and acoustic signal
processing engineers are ready to listen.

There have been a few proposals for benchmarks already, such as SLUE
and ASR-GLUE, both coined from the wildly popular General Language
Understanding Evaluation (GLUE) for text processing, but to date the
speech analogues of GLUE have been much humbler in both their breadth
and uptake.  At the same time, the same causes for concern exist as
for GLUE: is sentiment analysis actually a task?  What constitutes a
task in related HCI work would be something people want to perform and
could express (dis)satisfaction with, e.g., voice-mail interaction or
meeting summarization.  But this kind of vertical definition could
easily result in a proliferation of datasets and disagreements over
approaches.

The purpose of this track is to encourage proposals and proofs of
concept by both engineering and HCI researchers to converge on an
appropriate benchmark.

Topics include, but not limited to:

'       Individual task proposals
'       General criteria/desiderata for individual task proposals
'       Frameworks and codebases to support evaluation benchmarks
'       Case studies with existing benchmarks or ad hoc groups of tasks
'       Proposals of new intrinsic measures
'       Systemic considerations governing balance across tasks/measures
'       Automated proxies for human-subject evaluation

Contribution Types
-       Regular papers [in the proceedings, digital library]
-       Short papers (work in progress) [in the proceedings, digital library]
-       Posters: two pages [in the proceedings, digital library]
-       Posters: slide only [slide-deck posted on www.iaria.org]
-       Presentations: slide only [slide-deck posted on www.iaria.org]
-       Demos: two pages [posted on www.iaria.org]

Important Datelines
Inform the Chair: As soon as you decide to contribute
Submission: March 9 (earlier, better)
Notification: March 27
Registration: April 6
Camera-ready: April 6 Note: The submission deadline is somewhat flexible

Paper Format
- 6 pages on US-letter, plus up to 4 extra pages at additional cost
For further details, see: http://www.iaria.org/format.html

- Before submission, please check and comply with the editorial rules:
http://www.iaria.org/editorialrules.html

Publications
- Extended versions of selected papers will be published in IARIA
Journals: http://www.iariajournals.org
- Print proceedings will be available via Curran Associates, Inc.:
http://www.proceedings.com/9769.html
- Articles will be archived in the free access ThinkMind Digital Library:
http://www.thinkmind.org

Paper Submission
https://www.iariasubmit.org/conferences/submit/newcontribution.php?event=ACHI+2023+Special
Please select Track Preference as SATASK

Registration
- Each accepted paper needs at least one full registration, before the
camera-ready manuscript can be included in the proceedings.
- Registration fees are available at http://www.iaria.org/registration.html

Contact
Chair: Gerald Penn, gpenn@cs.toronto.edu
Logistics: steve@iaria.org

https://www.iariasubmit.org/conferences/submit/newcontribution.php?event=ACHI+2023+Special



Note: Onsite and Online Options

In order to accommodate a large number of situations, we are offering
the option for either physical presence or virtual participation. We
would be delighted if all authors manage to attend in person but are
aware that special circumstances are best handled by having flexible
options.

Back

Top

Dear colleagues and prospective participants of HISPhonCog 2023

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

• A PDF file of a two-page abstract (single-spaced with 12 pt font size *without* a list of authors’ names and their affiliations) should be submitted through EasyChair by February 10, 2023.
• URL for EasyChair: https://easychair.org/conferences/?conf=hisphoncog2023 (If the link does not work, please check http://site.hanyang.ac.kr/web/hisphoncog for an update.)

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

• Contact person: Dr. Suyeon Lim at hanyang.hipcs@gmail.com
• https://site.hanyang.ac.kr/web/hisphoncog/about-hisphoncog/2023

Back

Top

Dans le cadre des conférences conjointes CORIA-TALN 2023 organisées à Paris, nous sollicitons des propositions d'ateliers. Les ateliers doivent porter sur une thématique particulière de traitement automatique des langues ou de recherche d’information afin de rassembler quelques exposés plus ciblés que lors des conférences plénières.

Chaque atelier a son propre président et son propre comité de programme. Le responsable de l'atelier est chargé de la communication sur celui-ci, de l'appel à soumissions et de la coordination de son comité de programme.

Les organisateurs de CORIA-TALN 2023 s'occuperont de la logistique (e.g. gestion des salles, pauses café et diffusion des articles).

Les ateliers auront lieu en parallèle durant une journée ou une demi-journée (2 à 4 sessions de 1h30) le lundi 5 juin 2023.

Dates importantes
- Date limite de soumission des propositions d'atelier : 6 février 2023
- Réponse du comité de programme : 13 février 2023

Modalités de proposition
Les propositions d'ateliers (1 à 2 pages A4 en format PDF) comprendront :
- le nom et l'acronyme de l’atelier
- une description synthétique du thème de l'atelier
- le comité d'organisation
- le comité scientifique provisoire ou pressenti
- l'adresse du site web
- la durée souhaitée pour la réalisation de l'atelier (1 journée ou 1/2 journée) et l'audience potentielle

Les propositions d'ateliers devront être envoyées sous forme électronique à adrian.chifu@univ-amu.fr et à cyril.grouin@limsi.fr avec pour entête de courriel : [Atelier CORIA-TALN 2023].

Modalités de sélection
Les propositions d'atelier seront examinées par des membres des comités de programme de CORIA, TALN, par l'ARIA et le CPERM de l'ATALA. Les critères suivants seront considérés pour acceptation :
- l'adéquation aux thèmes de l'une ou l'autre des conférences
- l'originalité de la proposition

Format
Les conférences auront lieu en français (ou en anglais pour les non-francophones). Les articles soumis devront suivre le format de CORIA-TALN 2023 (nombre de pages à la discrétion du comité de programme de l'atelier). La soumission des versions finales devra suivre le calendrier de la conférence principale.

Contact : adrian.chifu@univ-amu.fr et cyril.grouin@limsi.fr

Back

Top

ICMR2023 – ACM International Conference on Multimedia Retrieval

https://icmr2023.org/

Back

Top

====ACM ICMR 2023 Doctoral Symposium, Call for papers======== 

ACM ICMR 2023 https://icmr2023.org doctoral symposium plans to bring together Ph.D. students working on topics aligned with the topics of this year conference:

• Multimedia content-based search and retrieval,
• Multimedia-content-based (or hybrid) recommender systems,
• Large-scale and Web-scale multimedia retrieval,
• Multimedia content extraction, analysis, and indexing,
• Multimedia analytics and knowledge discovery,
• Multimedia machine learning, deep learning, and neural networks,
• Relevance feedback, active learning, and transfer learning,
• Fine-grained retrieval for multimedia,
• Event-based indexing and multimedia understanding,
• Semantic descriptors and novel high- or mid-level features,
• Crowdsourcing, community contributions, and social multimedia,
• Multimedia retrieval leveraging quality, production cues, style, framing, and affect,
• Synthetic media generation and detection,
• Narrative generation and narrative analysis,
• User intent and human perception in multimedia retrieval,
• Query processing and relevance feedback,
• Multimedia browsing, summarization, and visualization,
• Multimedia beyond video, including 3D data and sensor data,
• Mobile multimedia browsing and search,
• Multimedia analysis/search acceleration, e.g., GPU, FPGA,
• Benchmarks and evaluation methodologies for multimedia analysis/search,
• Privacy-aware multimedia retrieval methods and systems,
• Fairness and explainability in multimedia analysis/search,
• Legal, ethical and societal impact of multimedia retrieval research,
• Applications of multimedia retrieval, e.g., news/journalism, media, medicine, sports, commerce, lifelogs, travel, security, and environment.

We encourage contributions from students working in the full space of these topics, which is defined by dimensions including:

• Content: image, video, music, spoken audio, sensor data;
• Tasks: retrieval, recommendation, summarization, multimedia mining;
• Multiple modalities: multimodal fusion, cross-media retrieval;
• Algorithms: memory-based, rule-based, model-based, deep learning;
• Retrieval pipeline: hashing, indexing, representation, similarity metrics, query interpretation, results presentation;
• Interaction: relevance feedback, conversational and emotional interfaces;
• Relevance Criteria: topic, style, quality, intent;
• Challenges: large-scale data, fine-grained retrieval, evaluation, interfaces, crowdsourcing, privacy, new applications.

The doctoral symposium will take place during the main conference in a dedicated oral session. The goal is to provide a forum for Ph.D. students to present ongoing research in a collaborative environment and to share ideas with other renowned and experienced researchers. Participants will discuss their research ideas and results, and they will receive constructive feedback from an audience consisting of peers as well as more senior people. It will be an excellent opportunity for developing person-to-person networks to the benefit of the Ph.D. students in their future careers and also of the community.

The Ph.D. students of the accepted doctoral symposium papers coming at the conference to present solely their doctoral symposium paper will be entitled to a student registration fee for the entire conference.

Eligibility

Prospective student attendees should already have a clear direction for research, and possibly have published some results. Preference will be given to students who have advanced to Ph.D. candidacy.

Maximum Length of a Paper

Each doctoral symposium paper should not be longer than 4 pages.

Important Dates

• Paper Submission Due: February 17, 2023
• Notification of Acceptance: March 31, 2023
• Camera-Ready Papers Due: April 20, 2023

Single-Blind Review

ACM ICMR will use a single-blind review process for doctoral symposium paper selection. Authors should provide author names and affiliations in their manuscript. Selections will be based on the submitted 4 pages paper, singly authored by the student wishing to attend. Submissions will be reviewed by the Doctoral Symposium Committee (appointed by the Doctoral Symposium Chairs). Accepted proposals will be published in the conference proceedings. Doctoral students who submit to the Doctoral Symposium are encouraged to submit a paper on their research to the main conference. However, acceptance for participation in the Doctoral Symposium will be based solely on the paper written ad-hoc for the event. All papers will be reviewed with respect to overall quality of presentation, potential for future impact of the research on the field, and expected benefit to the other doctoral students attending the conference.

Submission Instructions

Applications to the Doctoral Symposium should include a 4 pages paper summarizing the applicant’s dissertation research. The paper should include:

• Abstract and the keywords;
• Motivation, problem description;
• Background and related work (including key references);
• Novelty and significance relative to the state of the art;
• Approach, data, methods and proposed experiments;
• Results obtained and work in progress;
• Specific research issues for discussion at the Doctoral Symposium.

In addition to the paper, the applicants are expected to provide a 1 page appendix that should describe the benefits that would be obtained by attending the Doctoral Symposium, including:

• A statement by the student saying why they want to attend the Symposium;
• A statement by their advisor saying how the student would benefit by attending the Symposium.

Advisors should also specifically state whether the student has written, or is close to completing, a thesis proposal (or equivalent), and when they expect the student would defend their dissertation if they progress at a typical rate.

The appendix should be uploaded as a separated file. See the Paper Submission section.

Contact

For any questions regarding demo submissions, please email the Doctoral Symposium Chairs:

Aisling Kelliher  aislingk@vt.edu

Jenny Benois-Pineau jenny.benois-pineau@u-bordeaux.fr

Back

Top

JPC 2023 - Toulouse du 15 au 17 juin 2023

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

3e Appel à Communication

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, ... 

Back

Top

Hae-Sung Jeon and colleagues are organizing a workshop titled Speech Prosody and Beyond,

June 20-23 in Seoul, with abstracts due February 5. 

Details are at https://ukskprosodynetwork.github.io/ .

Back

Top

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
DSTC11.T4)

Call for Participation

TRACK GOALS AND DETAILS: Two main goals and tasks:
•    Task 1: Propose and develop effective Automatic Metrics for evaluation of open-domain multilingual dialogs.
•    Task 2: Propose and develop Robust Metrics for dialogue systems trained with back translated and paraphrased dialogs in English.

Back

Top

We would like to welcome you to Prague for the 20th International Congress of the Phonetic Sciences (ICPhS), which takes place on August 7–11, 2023, in Prague, Czech Republic.

ICPhS takes place every four years, is held under the auspices of the International Phonetic Association and provides an interdisciplinary forum for the presentation of basic and applied research in the phonetic sciences. The main areas covered by the Congress are speech production, speech acoustics, speech perception, speech prosody, sound change, phonology, sociophonetics, language typology, first and second language acquisition, forensic phonetics, speaking styles, voice quality, clinical phonetics and speech technology.

We invite papers on original, unpublished research in the phonetic sciences. The theme of the Congress is “Intermingling Communities and Changing Cultures”. Papers related to this theme are especially encouraged, but we welcome papers related to any of the Congress’ scientific areas. The deadline for abstract submission is December 1, 2002, and for full-paper submission December 8, 2022.

We also invite proposals for special sessions covering emerging topics, challenges, interdisciplinary research, or subjects that could foster useful debate in the phonetic sciences. The submission deadline is May 20, 2022.

All information is available at https://www.icphs2023.org/, where it is also possible to register for email notifications concerning the congress.

Contact: icphs2023@guarant.cz

Back

Top

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>

Back

Top

We would like to bring to your notice the launch of the special session at Interspeech 2023 on DIarization of SPeaker and LAnguage in Conversational Environments [DISPLACE] Challenge.  

The DISPLACE challenge entails a first of kind task to perform speaker and language diarization on the same data, as the data contains multi-speaker social conversations in multilingual code-mixed speech. In multilingual communities, social conversations frequently involve code-mixed and code-switched speech. In such cases, various speech processing systems need to perform the speaker and language segmentation before any downstream task. The current speaker diarization systems are not equipped to handle multi-lingual conversations, while the language recognition systems may not be able to handle the same talker speaking in multiple languages within the same recording. 

With this motivation, the DISPLACE challenge attempts to benchmark and improve Speaker Diarization (SD) in multilingual settings and Language Diarization (LD) in multi-speaker settings, using the same underlying dataset. For this challenge, a natural multi-lingual, multi-speaker conversational dataset will be distributed for development and evaluation purposes. There will be no training data given and the participants will be free to use any resource for training the models. The challenge reflects the theme of Interspeech 2023 - 'Inclusive Spoken Language Science and Technology – Breaking Down Barriers' in its true sense.  

Registrations are open for this challenge which will contain two tracks - a) Speaker diarization track and b) Language diarization track. 

A baseline system and an open leaderboard is available to the participants. The DISPLACE challenge is split into two phases, where the first phase is linked to the Interspeech paper submission deadline, while the second phase aligns with the camera ready submission deadline. For more details, dates and to register, kindly visit the DISPLACE challenge website: https://displace2023.github.io/

We look forward to your team challenging to 'displace' the state-of-the-art in speaker, language diarization. 

Thank you and Namaste,

The DISPLACE team 

Back

Top

The Association for the Advancement of Affective Computing (AAAC) invites you to join us at our 11th International Conference on Affective Computing and Intelligent Interaction (ACII), which will be held in Cambridge, Massachusetts, USA,on September 10th – 13th, 2023. 

The Conference series on Affective Computing and Intelligent Interaction is the premier international venue for interdisciplinary research on the design of systems that can recognize, interpret, and simulate human emotions and, more generally, affective phenomena. All accepted papers are expected to be included in IEEE Xplore (conditional on the approval by IEEE Computer Society) and indexed by EI. A selection of the best articles at ACII 2023 will be invited to submit extended versions to the IEEE Transactions on Affective Computing.

The theme of ACII 2023 is “Affective Computing: Context and Multimodality”. Fully understanding, predicting, and generating affective processes undoubtedly requires the careful integration of multiple contextual factors (e.g., gender, personality, relationships, goals, environment, situation, and culture), information modalities (e.g., audio, images, text, touch, and smells) and evaluation in ecological environments. Thus, ACII 2023 especially welcomes submitted research that assesses and advances Affective Computing’s ability to do this integration.

Topics of interest include, but are not limited to:

Recognition and Synthesis of Human Affect from ALL Modalities

• Multimodal Modeling of Cognitive and Affective States

• Contextualized Modeling of Cognitive and Affective States

• Facial and Body Gesture Recognition, Modeling and Animation
• Affective Speech Analysis, Recognition and Synthesis
• Recognition and Synthesis of Auditory Affect Bursts (Laughter, Cries, etc.)
• Motion Capture for Affect Recognition
• Affect Recognition from Alternative Modalities (Physiology, Brain Waves, etc.)
• Affective Text Processing and Sentiment Analysis
• Multimodal Data Fusion for Affect Recognition
• Synthesis of Multimodal Affective Behavior
• Summarisation of Affective Behavior

Affective Science using Affective Computing Tools

• Studies of affective behavior perception using computational tools

• Studies of affective behavior production using computational tools

• Studies of affect in medical/clinical settings using computational tools

• Studies of affect in context using computational tools

Psychology & Cognition of Affect in Designing Computational Systems

• Computational Models of Affective Processes

• Issues in Psychology & Cognition of Affect in Affective Computing Systems

• Cultural Differences in Affective Design and Interaction 

Affective Interfaces

• Interfaces for Monitoring and Improving Mental and Physical Well-Being

• Design of Affective Loop and Affective Dialogue Systems

• Human-Centred Human-Behaviour-Adaptive Interfaces

• Interfaces for Attentive & Intelligent Environments

• Mobile, Tangible and Virtual/Augmented Multimodal Proactive Interfaces

• Distributed/Collaborative Multimodal Proactive Interfaces

• Tools and System Design Issues for Building Affective and Proactive Interfaces

• Evaluation of Affective, Behavioural, and Proactive Interfaces

 Affective, Social and Inclusive Robotics and Virtual Agents

• Artificial Agents for Supporting Mental and Physical Well-Being
• Emotion in Robot and Virtual Agent Cognition and Action
• Embodied Emotion
• Biologically-Inspired Architectures for Affective and Social Robotics
• Developmental and Evolutionary Models for Affective and Social Robotics
• Models of Emotion for Embodied Conversational Agents
• Personality in Embodied Conversational Agents
• Memory, Reasoning, and Learning in Affective Conversational Agents

Affect and Group Emotions

• Analyzing and modeling groups taking into account emergent states and/or emotions

• Integration of artificial agents (robots, virtual characters) in the group life by leveraging its affective loop: interaction paradigms, strategies, modalities, adaptation

• Collaborative affective interfaces (e.g., for inclusion, for education, for games and entertainment)

Open Resources for Affective Computing

• Shared Datasets for Affective Computing

• Benchmarks for Affective Computing

• Open-source Software/Tools for Affective Computing

Fairness, Accountability, Privacy, Transparency and Ethics in Affective Computing   

• Bias, imbalance and inequalities in data and modeling approaches in the context of Affective Computing

• Bias mitigation in the context of Affective Computing

• Explainability and Transparency in the context of Affective Computing

• Privacy-preserving affect sensing and modeling

• Ethical aspects in the context of Affective Computing

Applications

• Health and well-being
• Education
• Entertainment
• Consumer Products
• User Experience

Important dates

Main track submissions: 14 April 2023

Decision notification to authors: 2 June 2023

Camera ready submission for main track: 16 June 2023

The remaining important dates can be found at the ACII website.

We hope to see you at ACII 2023!

ACII2023 Organizers

AFFECTIVE COMPUTING & INTELLIGENT INTERACTION

Back

Top

The 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) and the 16th International Natural Language Generation Conference (INLG) will be held jointly in Prague on September 11-15, 2023.

The SIGDIAL venue provides a regular forum for the presentation of cutting edge research in dialogue and discourse to both academic and industry researchers, continuing a series of 23 successful previous meetings. The conference is sponsored by the SIGDIAL organization - the Special Interest Group in discourse and dialogue for ACL and ISCA.

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. Discourse issues in text generated by large language models.

  *   Dialogue Systems: Task oriented and open domain spoken, multi-modal, embedded, situated, and text-based dialogue systems, their components, evaluation and applications. Knowledge representation and extraction for dialogue. State representation, 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. Safety and ethics issues in Dialogue.

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

  *   Pragmatic and Semantic Modeling: Pragmatics and semantics of conversations(i.e., beyond a single sentence), e.g., rational speech act, conversation acts, intentions, conversational implicature, presuppositions.

  *   Applications of Dialogue and Discourse Processing Technology.

Submissions

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

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

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

  *   Demo descriptions should be no longer than 4 pages including title, text, examples, figures, tables and references. A separate one-page document should be provided to the program co-chairs for demo descriptions, specifying furniture and equipment needed for the demo.

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

Multiple Submissions

SIGDIAL 2023 cannot accept work for publication or presentation that will be (or has been) published elsewhere and that have been or will be submitted to other meetings or publications whose review periods overlap with that of SIGDIAL. Overlap with the SIGDIAL workshop submissions is permitted for non-archived workshop proceedings. Any questions regarding submissions can be sent to program-chairs [at] sigdial.org.

Blind Review

Building on previous years’ move to anonymous long and short paper submissions, SIGDIAL  2023 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, which are available as an Overleaf template and also downloadable directly (Latex and Word)

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

Submission Deadline

SIGDIAL will accept regular submissions through the Softconf/START system, as well as commitment of already reviewed papers through the ACL Rolling Review (ARR) system.

Regular submission

Authors have to fill in the submission form in the Softconf/START system and upload an initial pdf of their papers before May 15, 2023 (23:59 GMT-11).  Details and the submission link will be posted on the conference website.

Submission via ACL Rolling Review (ARR)

Please refer to the ARR Call for Papers for detailed information about submission guidelines to ARR. The commitment deadline for authors to submit their reviewed papers, reviews, and meta-review to SIGDIAL 2023 is June 19, 2023. Note that the paper needs to be fully reviewed by ARR in order to make a commitment, thus the latest date for ARR submission will be April 15, 2023.

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 2023 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.

SIGDIAL 2023 Program Committee

Svetlana Stoyanchev and Shafiq Rayhan Joty

Conference Website: https://2023.sigdial.org/

Back

Top

SIGDial/INLG Call for Workshop & Tutorial Proposals

The 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDial 2023) and the 16th International Natural Language Generation Conference (INLG 2023) will be held jointly in Prague on September 11-15, 2023. We now welcome the submission of workshop and tutorial proposals, which will take place on September 11 and 12 before the main conference. 

We encourage submissions of proposals on any topic of interest to the discourse, dialogue, and natural language generation communities. This program is intended to offer new perspectives and bring together researchers working on related topics. We especially encourage the sessions that would bring together researchers from SIGDial and INLG communities.  

Topics of interest include all aspects related to Dialogue, Discourse and Generation including (but not limited to) annotation and resources, evaluation, large language models, adversarial and RL methods, explainable/ethical AI, summarization, interactive/multimodal/situated/incremental systems, data/knowledge/vision-to-text, and applications of dialogue and NLG.

The proposed workshops/tutorials may include a poster session, a panel session, an oral presentation session, a hackathon, a generation/dialogue challenge, or a combination of the above. Workshop organizers will be responsible for soliciting, reviewing, and selecting papers or abstracts. The workshop papers will be published in a separate proceedings. Workshops may, at the discretion of the SIGDial/INLG organizers, be held as parallel sessions. 

Submissions

Workshop and Tutorial proposals should be 2-4 pages containing:  title, type (workshop or tutorial), a summary of the topic, motivating theoretical interest and/or application context; a list of organizers and sponsors; duration (half-day or full-day), and a requested session format(s): poster/panel/oral/hackathon session. Please include the number of expected attendees. The workshop proposals will be reviewed jointly by the general chair and program co-chairs.

Links

Those wishing to propose a workshop or tutorial may want to look at some of the sessions organized at recent SIGDial meetings:

Natural Language in Human Robot Interaction (NLiHRI 2022) https://2022.sigdial.org/call-for-papers-nlihri/
NLG4health 2022 https://nlg4health.uvt.nl/
SummDial 2021 https://elitr.github.io/automatic-minuting/summdial.html
SafeConvAI 2021  https://sites.google.com/view/safety4convai/home
RoboDIAL 2022 https://robodial.github.io/
BigScience Workshop: LLMs 2021 https://bigscience.huggingface.co/
Interactive Natural Language Technology for Explainable Artificial Intelligence 2019 
https://www.inlg2019.com/workshop
https://www.sigdial.org/files/workshops/conference18/sessions.htm
https://inlg2018.uvt.nl/workshops/


Important Dates

Mar 24, 2023: Workshop/Tutorial Proposal Submission Deadline
April 14, 2023: Workshops/Tutorials Notifications

The  proposals should be sent to conference@sigdial.org 

Back

Top

CALL FOR PAPERS  --  ACM IVA 2023

The annual ACM Conference on Intelligent Virtual Agents (IVA) is the premier international event for interdisciplinary research on the development, application, and evaluation of Intelligent Virtual Agents with a focus on the ability for social interaction, communication or cooperation. Such artificial agents can be embodied graphically (e.g. virtual characters, embodied conversational agents) or physically (e.g. social or collaborative robots). They are capable of real-time perception, cognition, emotion and action allowing them to participate in dynamic social environments. This includes human-like interaction qualities such as multimodal communication using facial expressions, speech, and gesture, conversational interaction, socially assistive and affective interaction, interactive task-oriented cooperation, or social behaviour simulation. IVAs are highly relevant and widely applied in many important domains including health, tutoring, training, games, or assisted living.

We invite submissions of research on a broad range of topics, including but not limited to: theoretical foundations of intelligent virtual agents, agent and interactive behaviour modelling, evaluation, agents in simulations, games, and other applications. Please see the detailed list of topics below.

VENUE

======

IVA 2023 will take place in Würzburg, Germany. Würzburg is a vibrant town located by the river Main in northern Bavaria, between Frankfurt and Nuremberg. The mix of stunning historical architecture and the young population is what makes the atmosphere so unique, including 35,000 students from three different universities. The mild and sunny climate is ideal to enjoy the many activities Würzburg has to offer: visiting a beer garden next to the river, attending a sporting or cultural event or taking a stroll through one of the parks.

IVA is targeted to be an in-person conference. In case of extraordinary circumstances, such as visa problems or health issues, video presentation will be possible. However, there is no digital or hybrid conference system planned, thus it is not possible to attend this year’s IVA conference remotely.

IMPORTANT DATES

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

Abstract submission: April 14, 2023

Paper submission: April 18, 2023

Review notification / start of rebuttal: May 31, 2023

Notification of acceptance: June 23, 2023

Camera ready deadline: July 18, 2023

Conference: September 19-22, 2023

All deadlines are anywhere on earth (UTC−12).

SPECIAL TOPIC

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

This year’s conference will highlight a special topic on “IVAs in future mixed realities”, e.g., in social VR and potential incarnations of a Metaverse. Immersive and potentially distributed artificial virtual worlds provide new forms of full-size embodied human-human interaction via avatars of arbitrary looks, enabling interesting intra- and interpersonal effects. They also enable hybrid avatar-agent interactions between humans and A.I.s, unlocking the full potential of non-verbal behavior in digital face-to-face encounters, significantly enhancing the design space for IVAs to assist, guide, help but also to persuade and affect interacting users. We specifically welcome all kinds of novel research on technological, psychological, and sociological determinants of such immersive digital avatar-agent encounters.

TYPES OF SUBMISSION

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

- Full Papers (7 pages + 1 additional page for references):

Full papers should present significant, novel, and substantial work of high quality.

- Extended Abstracts (2 pages + 1 additional page for references)

Extended abstracts may contain early results and work in progress.

- Demos (2 pages + 1 additional page for references +1 one page with demo requirements)

Demos submissions focus on implemented systems and should contain a link to a video of the system with a maximum length of 5 minutes.

All submissions will be double-blind peer-reviewed by a group of external expert reviewers. All accepted submissions will be published in the ACM proceedings.

Accepted full papers will be presented either in oral sessions or as posters during the conference (depending on the nature of the contribution), extended abstracts will be presented as posters, and demos will be showcased in dedicated sessions during the conference. For each accepted contribution, at least one of the authors must register for the conference.

IVA 2023 will also feature workshops and a doctoral consortium. Please visit the website (https://iva.acm.org/2023) for more details and updates.

TRACKS

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

For full paper submissions, IVA will have different paper tracks with different review criteria. Authors need to indicate which one of the following tracks they want to submit their paper to:

1. Empirical Studies

• criteria: methodology, theoretical foundation, originality of result etc.

2. Computational Models and Methods

• criteria: technical soundness, novelty of the model or approach, proof of concept, etc.

3. Operational Systems and Applications

• criteria: innovation of the application, societal relevance, evaluation of effects, etc.

SCOPE AND LIST OF TOPICS

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

IVA invites submissions on a broad range of topics, including but not limited to:

AGENT DESIGN AND MODELING:

- Cognition (e.g. task, social, other)

- Emotion, personality and cultural differences

- Socially communicative behaviour (e.g., of emotions, personality, relationship)

- Conversational and dialog behavior

- Social perception and understanding of other’s states or traits

- Machine learning approaches to agent modeling

- Adaptive behavior and interaction dynamics

- Models informed by theoretical and empirical research from psychology

MULTIMODAL INTERACTION:

- Verbal and nonverbal behavior coordination (synthesis)

- Multimodal/social behavior processing

- Face-to-face communication skills

- Interaction qualities  engagement, rapport, etc.)

- Managing co-presence and interpersonal relation

- Multi-party interaction

- Data-driven modeling

SOCIALLY INTERACTIVE AGENT ARCHITECTURES:

- Design criteria and design methodologies

- Engineering of real-time human-agent interaction

- Standards / measures to support interoperability

- Portability and reuse

- Specialized tools, toolkits, and toolchains

EVALUATION METHODS AND EMPIRICAL STUDIES:

- Evaluation methodologies and user studies

- Metrics and measures

- Ethical considerations and societal impact

- Applicable lessons across fields (e.g. between robotics and virtual agents)

- Social agents as a means to study and model human behavior

APPLICATIONS:

- Applications in education, skills training, health, counseling, games, art, etc.

- Virtual agents in games and simulations

- Social agents as tools in psychology, neuroscience, social simulation, etc

- Migration between platforms

INSTRUCTIONS FOR AUTHORS

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

Paper submissions should be anonymous and prepared in the “ACM Standard” format, more specifically the “SigConf” format. Please consulthttps://www.acm.org/publications/proceedings-template for the Latex template, word interim template, or connection to the overleaf platform.

All papers need to be submitted in PDF-format.

By submitting your article to an ACM Publication, you are hereby acknowledging that you and your co-authors are subject to all ACM Publications Policies, including Publications Policy on Research Involving Human Participants and Subjects. Alleged violations of this policy or any ACM Publications Policy will be investigated by ACM and may result in a full retraction of your paper, in addition to other potential penalties, as per ACM Publications Policy.

Please ensure that you and your co-authors obtain an ORCID ID, so you can complete the publishing process for your accepted paper.  ACM has been involved in ORCID from the start and we have recently made a commitment to collect ORCID IDs from all of our published authors.  The collection process has started and will roll out as a requirement throughout 2022.  We are committed to improve author discoverability, ensure proper attribution and contribute to ongoing community efforts around name normalization; your ORCID ID will help in these efforts.

The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of the conference. The official publication date affects the deadline for any patent filings related to published work.

This event is sponsored by SIGAI.

Please visit the conference website for detailed information on how to submit your paper.

CONFERENCE WEBSITE

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

https://iva.acm.org/2023/

Back

Top

Call for SS  Proposals at CBMI’2023==================

CBMI’2023  http://cbmi2023.org/ is calling for high quality Special Sessions  addressing innovative research in content – based multimedia indexing  and its related broad fields. The main scope of the conference is in  analysis and understanding of multimedia contents including

• Multimedia information retrieval (image, audio, video, text)
• Mobile media retrieval
• Event-based media retrieval
• Affective/emotional interaction or interfaces for multimedia retrieval
• Multimedia data mining and analytics
• Multimedia retrieval for multimodal analytics and visualization
• Multimedia recommendation
• Multimedia verification (e.g., multimodal fact-checking, deep fake analysis)
• Large-scale multimedia database management
• Summarization, browsing, and organization of multimedia content
• Evaluation and benchmarking of multimedia retrieval systems
• Explanations of decisions of AI-in Multimedia
• Application domains : health, sustainable cities, ecology, culture… 

and all this in the era of Artificial Intelligence for analysis and indexing of multimedia and multimodal information.

A special oral session will contain oral presentations of long research papers, short papers will be presented as posters during poster sessions with special mention of an SS.

-        Long research papers should present complete work with evaluations on topics related to the Conference.

-        Short research papers should present preliminary results or more focused contributions.

-         

An SS proposal has to contain

-        Name, title, affiliation and a short bio of SS chairs;

-        The rational ;

-         A  list of at least 5 potential contributions with a provisional title, authors and affiliation.

The dead line for SS proposals is coming:  23rd of January

Please submit your proposals to the SS chairs

jenny.benois-pineau@u-bordeaux.fr

mourad.oussalah@oulu.fi

adel.hafiane@insa-cvl.fr

Back

Top

25th ACM International Conference on Multimodal Interaction (ICMI 2023)

9-13 October 2023, Paris, France

The 25th International Conference on Multimodal Interaction (ICMI 2023) will be held in Paris, France. ICMI is the premier international forum that brings together multimodal artificial intelligence (AI) and social interaction research. Multimodal AI encompasses technical challenges in machine learning and computational modeling such as representations, fusion, data and systems. The study of social interactions englobes both human-human interactions and human-computer interactions. A unique aspect of ICMI is its multidisciplinary nature which values both scientific discoveries and technical modeling achievements, with an eye towards impactful applications for the good of people and society.

ICMI 2023 will feature a single-track main conference which includes: keynote speakers, technical full and short papers (including oral and poster presentations), demonstrations, exhibits, doctoral consortium, and late-breaking papers. The conference will also feature tutorials, workshops and grand challenges. The proceedings of all ICMI 2023 papers, including Long and Short Papers, will be published by ACM as part of their series of International Conference Proceedings and Digital Library, and the adjunct proceedings will feature the workshop papers.

Novelty will be assessed along two dimensions: scientific novelty and technical novelty. Accepted papers at ICMI 2023 will need to be novel along one of the two dimensions:

• Scientific Novelty: Papers should bring new scientific knowledge about human social interactions, including human-computer interactions. For example, discovering new behavioral markers that are predictive of mental health or how new behavioral patterns relate to children’s interactions during learning. It is the responsibility of the authors to perform a proper literature review and clearly discuss the novelty in the scientific discoveries made in their paper.
• Technical Novelty: Papers should propose novelty in their computational approach for recognizing, generating or modeling multimodal data. Examples include: novelty in the learning and prediction algorithms, in the neural architecture, or in the data representation. Novelty can also be associated with new usages of an existing approach.

Please see the Submission Guidelines for Authors https://icmi.acm.org/ for detailed submission instructions. Commitment to ethical conduct is required and submissions must adhere to ethical standards in particular when human-derived data are employed. Authors are encouraged to read the ACM Code of Ethics and Professional Conduct (https://ethics.acm.org/).

ICMI 2023 conference theme: The theme for this year’s conference is “Science of Multimodal Interactions”. As the community grows, it is important to understand the main scientific pillars involved in deep understanding of multimodal social interactions. As a first step, we want to acknowledge key discoveries and contributions that the ICMI community enabled over the past 20+ years. As a second step, we reflect on the core principles, foundational methodologies and scientific knowledge involved in studying and modeling multimodal interactions. This will help establish a distinctive research identity for the ICMI community while at the same time embracing its multidisciplinary collaborative nature. This research identity and long-term agenda will enable the community to develop future technologies and applications while maintaining commitment to world-class scientific research.

Additional topics of interest include but are not limited to:

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

Important Dates

Paper Submission: May 1, 2023 

Rebuttal period: June 26-29, 2023

Paper notification: July 21, 2023

Camera-ready paper: August 14, 2023

Presenting at main conference: October 9-13, 2023

Back

Top

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/

Back

Top