|
 |
ISCApad #318 |
| Wednesday, December 11, 2024 by Chris Wellekens |
3-3 Other Events
| 3-3-1 | (2024-12-13) TTS for low resource languages, dialects and accents, LIUM, LeMans, France The LIUM organize a scientific day entitled TTS for low resource languages, dialects and accents, on the 13/12/2024.
If you wish to come in-person in Le Mans, please confirm replying my email.
There is still some option to add few presentations in the program, so please let me know if you want I include new talks to the current organisation. In order to favor in-person discussions, please contact me if you have some financial difficulties for travelling to Le Mans.
Location : Bâtiment IC2 (Institut Claude Chappe) LIUM, Le Mans Université, 72000 Le Mans. Presentations will take place in the room 210, second floor.
Lien visio : GDR TAL // TTS for low resource languages, dialects and accents
Organizer: LIUM (Marie Tahon)
Currently, many different neural architectures are available on the shelf for Text-to-Speech (TTS). However it is not always easy to choose the best network for a given target application. Especially the limits and drawbacks of pre-trained models are not well defined. This can be crucial when addressing specific applications such as health, human-robot interactions, etc. or low resource languages, dialects or accents. Indeed, a TTS system usually involves a text processing module, (i.e. phonetization), an encoder which predicts a time-frequency representation and a vocoder which generates the speech signal itself. In order to process these different modules, one needs to collect audio data, get its linguistic or phonetic transcription. To do so NLP tools (such as the phonetizer) must be adapted to their specific languages. The evaluation of synthetic speech is the last bottleneck: indeed it is not always easy to find native speakers who are able to accurately evaluate a synthetic speech signal in their own language as the acculturation with synthetic speech is not uniform across languages.
The aim of this day is to get an overview of 1) the difficulties to collect, process and manage low resource speech data, 2) how existing architectures are robust to the low resource languages, and 3) the evaluation protocol when native speakers are rare.
Organisation of day (draft version)
10h introduction
10h15 Kévin Vythelingum (Voxygen) Speech synthesis with a foreign accent from low-resource speaker using self-supervised model representations
11h15 Emmett Strickland (MoDyCo) Experimental and corpus-based phonetics in Nigerian Pidgin: Challenges and perspectives
12h15 lunch
13h30 Marc Evrard et Philippe Boula de Mareuil (LISN) Speech synthesis for Wallon belge accent.
14h30 Imen Laouirine, Fethi Bougares (Elyadata) Transfer Learning based Tunisian Arabic Text-to-Speech System.
15h30 Ana Montalvo (CENATAV) Investigations for TTS in spanish cuban accent.
16h30 round table and discussions
17h end of day
Detailed program:
Kévin Vythelingum (Voxygen) Speech synthesis with a foreign accent from low-resource speaker using self-supervised model representations
Self-supervised pretrained models, like Wav2Vec [1], HuBERT [2] or WavLM [3], exhibit excellent performances on many speech tasks such has speech enhancement, automatic speech recognition or speaker diarization. As a result, it shows that representations of these models carry both language and speaker informations. Especially, the authors of kNN-VC [4] demonstrates voice conversion capabilities of WavLM features. Regarding text-to-speech, it is often difficult to model speakers with underrepresented characteristics, like a specific accent. In order to adress this problem, we investigate the use of WavLM features to transfer the accent of speakers to a generic text-to-speech model in a low-resource scenario.
[1] Baevski, Alexei, et al. 'wav2vec 2.0: A framework for self-supervised learning of speech representations.' Advances in neural information processing systems 33 (2020): 12449-12460.
[2] Hsu, Wei-Ning, et al. 'Hubert: Self-supervised speech representation learning by masked prediction of hidden units.' IEEE/ACM transactions on audio, speech, and language processing 29 (2021): 3451-3460.
[3] Chen, Sanyuan, et al. 'Wavlm: Large-scale self-supervised pre-training for full stack speech processing.' IEEE Journal of Selected Topics in Signal Processing 16.6 (2022): 1505-1518.
[4] Baas, Matthew, Benjamin van Niekerk, and Herman Kamper. 'Voice conversion with just nearest neighbors.' arXiv preprint arXiv:2305.18975 (2023).
Emmett Strickland (MoDyCo) Experimental and corpus-based phonetics in Nigerian Pidgin: Challenges and perspectives
This talk will present ongoing research aimed at studying the role of pitch and duration in Nigerian Pidgin, a low-resource language of West Africa. The presentation will describe a novel syntactic treebank which combines traditional morphosyntactic annotations with a wide range of phonetic features describing the segmental and suprasegmental features of each syllable. This treebank will then be used to shed light on the prosody of certain syntactic constructions, with a focus on preverbal markers of tense, aspect, and mood (TAM). Finally, the presentation will describe efforts to implement perceptive experiments to validate the findings from the exploration of the corpus. This is carried out using a pitch-controllable text-to-speech system trained on pre-existing field recordings. This portion of the presentation will notably highlight the difficulties in building a task-specific TTS system from a noisy corpus of spontaneous speech which was not made with speech synthesis in mind.
Imen Laouirine, Fethi Bougares (Elyadata) Transfer Learning based Tunisian Arabic Text-to-Speech System.
Being labeled as a low-resource language, the Tunisian dialect has no existing prior TTS research. At elyadata we collected a a mono-speaker speech corpus of +3 hours of a male speaker sampled at 44100 kHz called TunArTTS. This corpus is processed, manually diacritized and used to initiate the development of end-to-end TTS systems for the Tunisian dialect. Various TTS systems using from scratch training and transfer learning were experimented and compared. TunArTTS corpus is publicly available for research purposes along with the baseline TTS system demo.
Ana Montalvo (CENATAV) Speech synthesis for Cuban Spanish accent
To be defined
Marc Evrard et Philippe Boula de Mareuil (LISN) Speech synthesis for Wallon belge accent.
We present a text-to-speech system for Walloon, a minority language spoken in Belgium and France. For this project, we used an audio corpus derived from a translation of Petit Prince. A native speaker was recorded to create the corpus. It was segmented into sentences and phonetized by an automatic (rule-based) system developed in-house specifically for Walloon. The synthesis system is based on the VITS architecture (Variational Inference with adversarial learning for end-to-end Text-to-Speech). Several models were trained under different conditions: individual speaker, phonetic and graphemic transcription, with and without fine-tuning from a model pre-trained on a French language corpus. An objective evaluation has been carried out and a perceptive evaluation campaign by native speakers is currently underway. As things stand, the objective evaluation does not allow us to clearly distinguish a trend between the different models. However, perceptually, it seems that fine-tuning models are preferred only when the training condition corresponds to the reduced corpus.
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-2 | (2024-12-18) Speech Prosody Lecture Series (on line) Speech prosody and social meaning Robert Xu, Harvard University
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-3 | (2025-03-03) VOICE AND SPEECH SCIENCE IN THE AGE OF ARTIFICIAL INTELLIGENCE (on line) I would like to personally encourage you to attend our online 2025 conference and hopefully submit an abstract for the special conference entitled VOICE AND SPEECH SCIENCE IN THE AGE OF ARTIFICIAL INTELLIGENCE. Our keynote speakers are Frank Guenther and Shri Narayanan, international experts on this topic. The conference is organized by the National Center for Voice and Speech (NCVS) and scheduled for March 3-4, 2025, only a few months away. Here are some topics that would fit into the general theme:
Abstract submission is extended to January 6, 2025. You can submit an abstract here: https://forms.gle/aTEevwHnTzvVTBQr7 NCVS is committed to bringing new areas of science to the voice and speech community. Cordially, Ingo R. Titze, PhD President, National Center for Voice and Speech
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-4 | (2025-03-25) Advanced Language Processing School (ALPS) 2025, Aussois (French Alps), France FIRST CALL FOR PARTICIPATION
Advanced Language Processing School (ALPS) 2025 March 30th - April 4th 2025 Aussois (French Alps)
We are pleased to announce the 5th edition of ALPS - the Advanced NLP School to be held in the French Alps from March 30th to April 4th 2025. This school targets advanced research students in Natural Language Processing and related fields and brings together world leading experts and motivated students. The programme comprises lectures, poster presentations, practical lab sessions and nature activities - the venue is located near a National Park.
Important Dates
Confirmed speakers so far:
Website and online application: https://alps.imag.fr/ Questions: alps@univ-grenoble-alpes.fr
The registration fees for the event encompass accommodation and full board at the conference venue, the Centre Paul Langevin. We will announce the fee amounts later, and they will vary depending on the participant's background: students, academia, and industry. Student fees will be set at or below €600, including twin room accommodation. We will have a limited amount of scholarships for the registration: if you are interested please mark this in the application form. The rates for academia and industry will be higher, as is customary, and will include accommodation in a single room.
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-5 | (2025-04-06) Call for ICASSP 2025 Grand Challenge, Hyberabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-6 | (2025-04-06) CfP ICASSP 2025, Hyderabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-7 | (2025-04-06) CfShort courses/ ICASSP2025, Hyderabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-8 | (2025-04-06) CfW ICASSP 2025, Hyderabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-9 | (2025-04-06) Deadlines for ICASSP 2025, Hyderabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-10 | (2025-04-06)Cf Tutorials, IEEE ISCASSP 2025, Hyderabad, India
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-11 | (2025-04-22) Call for Science: 2025 Voice AI Symposium, Tampa, FL, USA Call for Science: 2025 Voice AI Symposium hosted by the Bridge2AI-Voice Consortium
Submit your innovative research and technology to shape the future of AI and voice biomarkers! This year's theme is 'Translating AI Research into Reality: Implementing Voice Biomarkers for Transformative Healthcare'
Important Dates Submission Deadline for Abstracts: December 15th, 2024 Selection Notifications begin January 15th, 2025 Symposium + Hackathon Dates: April 22-24, 2025
We are welcoming submissions for the following categories Podium or Poster Presentations Panel Discussions Voice AI Technology Fair
About: The Bridge 2AI Voice Symposium is more than a conference; it is an interactive and collaborative effort between three integral aspects which impact our understanding of artificial intelligence (AI) and machine learning (ML): people, ethics, and data. Submit your groundbreaking work for consideration to be a part of the 2024 Bridge 2AI Voice Symposium. Come join a global network of pioneers and collaborate with patients, scientists, clinicians, and industry. You play a pivotal role in shaping the future of AI and ML. We will see you in sunny Tampa Florida April 22-24.
CATEGORY 1: PODIUM AND POSTER PRESENTATION ABSTRACTS
Abstracts will be accepted for the presentation of research. We will be accepting presentations in the format of (1) oral presentation (30 minute oral presentation), (2) poster, or (3) either format. Reviewers will evaluate the submission and determine the best fit for presentation.
The goals of the podium and poster sessions are to:
Topic Areas for Submission: We invite proposals for topics including but not limited to:
Topic Area 1: The reliability of Voice AI in clinical diagnostics and prediction. Subjects can include specific disorders, public health, health policy and organization, and accessibility. Proposals can target clinician workflow, home health, virtual screening etc. Focus on tangible solutions rather than broad ideas. Current projects or new projects/ideas can be included.
Topic Area 2: Validation of Voice AI processes and demonstrations of robustness. Subjects can include optimizing machine learning for voice data or identification of explicit and implicit biases in current clinical practice that could be exacerbated by voice AI. Topics should address mitigation strategies or systematic approaches to overcome these challenges.
Topic Area 3: How can we build trust and transparency in voice AI, ensuring that it is used in responsible and effective ways to improve health outcomes and transform healthcare? Practical solutions presented can cover: highlighting methods to promote data privacy and security while fostering data sharing for research innovation, respecting patients’ rights, addressing biases and unintended consequences, and establishing a clear and consistent legal framework for voice AI in healthcare.
Abstract Guidelines
Specifications and submission details: There is no submission fee. Abstracts will be reviewed by committee who will determine best presentation for research (either poster or podium) Podiums will be 30-minute oral presentations that offer valuable insights into the field of voice AI. Submissions should focus on either research or clinical applications of AI in voice. Research Presentations: Share recent findings or ongoing research that advances our understanding of voice AI]. Clinical Presentations: Highlight innovative approaches to diagnosis, treatment, or service delivery for voice AI. Discuss the practical implications and benefits of your methods. Abstracts should include: an introduction stating its relevance to improving human health, approach, preliminary findings (if available), conclusion, and future direction of your work. Maximum character count per abstract submission is 1,900 characters NOT including spaces. If you choose to add an image or table to your abstract submission, it will count as 600 characters towards the total 1,900 characters that are allowed.
CATEGORY 2: PANEL PRESENTATION ABSTRACT
We invite abstracts for panel presentations that address the effective development and use of AI in healthcare. Each panel will consist of a moderator and 3-4 presenters who will address moderator questions or present brief papers related to a specific topic. The panel session length will be approximately 60 minutes, and should include interaction with the audience through live polling questions, which we will facilitate through the use of 'Aha Slides' at the day of the event. The topic should be addressed within the context of our 3 key pillars – people, data, and ethics. The organizer of the symposium is expected to be the chair. Diversity of background and expertise within the panel is encouraged.Presenters should represent different laboratories and an international mix of contributors is encouraged.
Specifications and submission details: There is no submission fee. Panel presentation abstracts should include bullets that include: a title, name and affiliation of the moderator, a list of the panelists, and an abstract describing the intent of the panel presentation. The abstract should include a brief overview of the panel presentation, a description of the structure of the presentation, the purpose and the intended outcome(s). The abstract should include 5 questions relevant to your panel that will be used in interactive 'Aha slides' on the day of the event (e.g. 'How do you think voice biomarkers are most likely to be implemented in the next year?' plus four answers for the audience to choose from) Maximum character count per panel submission is 1,900 characters NOT including spaces. If you choose to add an image or table to your abstract submission, it will count as 600 characters towards the total 1,900 characters that are allowed.
CATEGORY 3: CALL FOR TECHNOLOGY - VOICE AI TECH FAIR
A technology fair will be hosted during the 2025 Bridge 2AI Voice Symposium. Eligible participants include startup companies, independent tech researchers and voice AI companies with relevant technology for demonstration. Technology should be relevant to applications of Voice AI or voice biomarkers in healthcare. Participants will have the opportunity to interact with clinicians, scientists, and patients to discuss and provide hands on interactions with their tech.
Specifications and submission details:
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-12 | (2025-04-27) CfP Congrès Français d’Acoustique, Sorbonne Université, Paris Nous avons le plaisir de vous informer que le prochain Congrès Français d’Acoustique (https://cfa2025.fr), organisé sous l’égide de la Société Française d’Acoustique (SFA), se tiendra sur le Campus Pierre et Marie Curie de Sorbonne Université du 27 au 30 Avril 2025. L'Association Francophone de la Communication Parlée (AFCP) est société partenaire pour l'organisation avec le Groupe d'Acoustique de la Parole (GAP-SFA) d'une session générale intitulée : acoustique de la voix, de la parole et du chant. Cette session a pour objectif de donner un aperçu des recherches scientifiques actuelles en sciences phonétiques et en acoustique : études expérimentales, travaux en modélisation et simulation, en phonétique expérimentale et clinique, analyse et synthèse, et histoire des sciences de la parole. Nous vous sollicitons aujourd’hui pour soumettre un résumé pour une communication orale à ce congrès. Le format d'un résumé est entre 120 et 300 mots, en langue française de préférence. Le résumé et les différentes informations saisies restent modifiables jusqu’à la date limite de contribution fixée au 01 décembre 2024. Nous espérons que vous pourrez y participer pour présenter vos derniers travaux. Veuillez noter que vous devez effectuer une pré-inscription avant de soumettre votre résumé, vous engageant ainsi à payer ultérieurement les frais d’inscription. Après avoir pris connaissance des informations sur l’inscription et la soumission des résumés sur https://cfa2025.fr/ , vous pourrez procéder à l’inscription en vous enregistrant sur la plateforme https://conforg.fr/bin/IA/reg_cfa2025_fr puis en utilisant les identifiants pour soumettre votre résumé sur https://conforg.fr/bin/usrlogin_cfa2025. À la première étape, choisissez 'GAP - Voix et Parole' dans le menu déroulant nommé 'Thème', puis 'Session générale d'acoustique de la voix, de la parole et du chant' dans le menu déroulant 'Session spéciale'. En espérant que vous accepterez cette invitation à participer, nous vous remercions par avance pour votre contribution à la réussite de cette manifestation. Bien cordialement, Nathalie Henrich Bernardoni, Coriandre Vilain et Claire Pillot-Loiseau
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-13 | (2025-05-16) CfP 3rd International Conference on Tone and Intonation - TAI 2025, Herrsching, Germany Call for Papers 3rd International Conference on Tone and Intonation - TAI 2025
We are delighted to announce that the Third International Conference on Tone and TAI 2025 will be held in Herrsching near Munich, Germany, from 16–18 May 2025. Jointly sponsored by the International Speech Communication Association (ISCA) and the International Phonetic Association (IPA), TAI 2025 will be hosted by the Institute for Phonetics and Speech Processing of the LMU Munich.
Sireemas Maspong
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-14 | (2025-06-09?) Cf research proposals: 2025 Jelinek Workshop on Speech and Language Technologies (JSALT), Brno, Czech Republic
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-15 | (2025-06-10) 10èmes Journées de Phonétique Clinique, Sète, France 10e Journées de Phonétique Clinique
En 2025, les 10e JPC auront lieu dans la proche région de Montpellier, à Sète du 10 au 12 Juin 2025. Elles seront organisées conjointement par l’équipe d’Anthropologie Évolutive de l’ISEM UMR5554 (CNRS & Université de Montpellier), le laboratoire Praxiling UMR5267 (CNRS & Université Paul Valéry Montpellier 3), le CHU Gui de Chauliac (Service Voix Parole Déglutition), le Laboratoire Audiocampus (Faculté de Pharmacie) et le Département Universitaire d’Orthophonie (Faculté de Médecine). Ces journées pluridisciplinaires sont principalement destinées à rassembler et à favoriser les échanges entre chercheurs, cliniciens et phonéticiens et avec tout autre professionnel s’intéressant aux mécanismes de production et de perception de la parole. Les JPC accueillent autant les experts que les jeunes chercheurs et les étudiants, des domaines cliniques (médecine, orthophonie, audiologie), psychologique, et des sciences du langage. Elles concernent tout ce qui a trait au langage, à la parole et à la voix de l’enfant et de l’adulte, sain ou atteint d’une pathologie. Ces aspects y sont 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. Les Journées de Phonétique Clinique offrent aux jeunes chercheurs une plateforme d'échange et de formation en contact direct avec des experts du domaine. Ils peuvent y présenter leurs travaux, recevoir des retours critiques, et assister à des conférences spécialisées, ce qui favorise l'acquisition de nouvelles compétences méthodologiques et théoriques. Cette immersion dans un cadre scientifique et collaboratif enrichit leur parcours académique, soutient leur développement professionnel en recherche clinique et linguistique et leur ouvre des perspectives d’avenir pour la suite de leur parcours universitaire (post-docs). Lors de cette 10e édition, les femmes, grandes oubliées de la recherche, seront mises à l’honneur. En effet, la recherche biomédicale vise à comprendre le fonctionnement, normal ou pathologique, du corps humain, afin d’améliorer la santé et la qualité de vie des individus. Que ce soit dans son volet clinique ou dans le domaine fondamental, elle s’est souvent cantonnée à des études sur des individus masculins sans tenir compte du fait que la prévalence de certaines maladies diffère selon le genre (Baggio et al. 2013). Ainsi, à l’heure actuelle, 60% des études publiées ne font aucunement mention du genre. La communauté scientifique a aujourd’hui pris conscience de l’importance d’inclure suffisamment de femmes dans les études et d’analyser ces données en fonction du genre. Les propositions de communication porteront sur les problématiques suivantes (liste non exhaustive) :
Dates importantes (site internet de soumission à venir) Date d’appel à communication : 12/11/2024 ***Date limite de réception des soumissions (abstracts de 500 mots) : 31/01/2025 Date de notification aux auteurs : 17/03/2025 Dates d’inscription (early-bird) : 17/03/2025 au 14/04/2025 inclus Date d’inscription (tarif normal) : 15/04/2025 au 02/06/2025 inclus Version finale des résumés : 16/05/2025
10e Journées de Phonétique Clinique : 10-12 juin 2025
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-16 | (2025-06-18) PAC 2025 - Spoken English Varieties - Perception and Representations, Aix-en-Provence,France (extended deadline) Deuxième appel à communications pour la conférence internationale PAC 2025 (phonologie de l’anglais contemporain) - Spoken English Varieties - Perception and Representations, qui se tiendra à Aix-en-Provence du 18 au 20 juin 2025. La conférence sera suivie le 20 juin après-midi d’un atelier sur le dépôt et le partage des données.
Dates à retenir : Conférence : 18-20 juin 2025, Laboratoire Parole et Langage, Aix-en-Provence. Date de soumission des résumés: 5 janvier 2025 Bien cordialement, Le comité d’organisation PAC 2025.
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-17 | (2025-06-23) CfP Forum Acusticum Euronoise 2025, Malaga, Spain Call for Submissions:
Special Session on Speaker Characterization: Speaker Recognition, Diarization, Speech Emotion Recognition We are pleased to invite you to submit your work to the Special Session on Speaker Recognition, Diarization, and Speech Emotion Recognition at the upcoming Forum Acusticum Euronoise 2025, to be held from 23rd to 26th of June 2025 in Malaga. This session will focus on cutting-edge research in the fields of speech analysis, with particular emphasis on speaker recognition, diarization, and the recognition of speech-based emotions. We welcome two types of submissions: 1. Oral Presentation of Published Work: Authors of previously published journal articles related to the session’s theme are invited to submit an abstract for an oral presentation of their work. This is an excellent opportunity to showcase your research to an interdisciplinary audience and engage in discussions. 2. Full Paper Submissions for Review: Authors with unpublished research are invited to submit their full papers for review. Accepted papers will be published in the conference proceedings and will also be eligible for oral presentation during the special session. Important Dates: - Abstract Submission Deadline: January 19th - Full Paper Submission Deadline: March 23rd - Notification of Acceptance: April 10th - Conference Dates: 23rd to 26th of June Submission Guidelines: - Abstracts for oral presentations of published work should be no more than 200 words. - Full paper submissions should be 2-4 pages for short papers, and up to 8 pages for long papers. - Detailed instructions can be found on the conference website https://www.fa-euronoise2025.org/ We look forward to your contributions and hope to see you at Forum Acusticum Euronoise 2025! For more information, please contact: Thomas Thebaud, PhD Assistant Research Scientist, Center for Language and Speech Processing Johns Hopkins University tthebau1@jhu.edu
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-18 | (2025-06-25) CfP : Prosody in Languages of the Middle East , Palma de Mallorca, Spain
Call for Papers: Prosody in Languages of the Middle East
Meeting Email: papeprosodyworkshop@gmail.com ; niamh.kelly@newcastle.ac.uk Webpage: https://agenda.uib.es/120122/section/53647/6th-phonetics-and-phonology-in-europe-pape-2025.html
Organisers
Meeting Description: Abstract guidelines: Max. 1 page for the body of the abstract (font size 11-12) and max. 1 page for figures/references. Please submit your abstracts to: papeprosodyworkshop@gmail.com Oral sessions: 10 min talk, 5 mins for Q&A. There will also be a poster session.
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-19 | (2025-07-20) CfP 61st IEEE Professional Communication Conference (ProComm), University of Southern Denmark, Sonderborg, Denmark Call for Papers for the 61st IEEE Professional Communication Conference (ProComm)
20-23 July 2025 at the University of Southern Denmark, Sonderborg, Denmark.
ProComm is the flagship conference of the IEEE Professional Communication Society.
The conference takes place under the theme: “Digital Solutions and Multimodal Challenges”
Modern communication calls for more than traditional methods today. Digital solutions play a crucial role as they expand the efficiency and reach of communication. Multimodal communication, an evolution of this trend, is about the challenge of seamlessly integrating various media forms, from messaging apps to video calls – and it is also about the challenge of understanding how the different type and layers of communication, text and images, speech and body language, interact and interfere in the creation of attractive and effective messages. In an increasingly interconnected world, the integration of digital solutions and multimodal communication is crucial for effective exchange and collaboration. While, of course, inviting papers from all areas of professional communication, the conference will put a focus on building such inter-disciplinary bridges, using our Acoustics Lab’s international network to invite (foreign) language teachers, public-speaking coaches, researchers from the speech sciences, and speech-communication engineers to the event.
The 2025 issue of the conference is hosted by the CIE Acoustics Lab at the University of Southern Denmark in Sonderborg, Denmark.
Conference website: https://event.sdu.dk/procomm2025
All papers are subject to two rounds of double-bling peer review, and accepted papers will be published as proceedings in IEEE Xplore®, see here for further information and indexing: https://ieeexplore.ieee.org/Xplorehelp/overview-of-ieee-xplore/about-content
Please note that the website for the 2025 conference is constantly updated. Information about keynotes, important dates etc. follow in autumn 2024.
*****************************************
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-20 | (2025-09-06) Labs @CLEF2025, Madrid, Spain
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-21 | (2025-09-08) EUSIPCO 2025, Palermo, Italy
| |||||||||||||||||||||||||||||||||||||||||||||||||||
| 3-3-22 | (2025-11-06) The First VoicePrivacy Attacker Challenge, ICASSP 2025, Hyderabad, India The First VoicePrivacy Attacker Challenge
**********************
Dear colleagues,
Registration for The First VoicePrivacy Attacker Challenge is now open!
The First VoicePrivacy Attacker Challenge is supported by ICASSP 2025 as the SP Grand Challenge (https://2025.ieeeicassp.org/sp-grand-challenges/#gc7). It focuses on developing attacker systems against voice anonymization, which will be evaluated against a set of anonymization systems submitted to the VoicePrivacy 2024 Challenge. Training, development, and evaluation datasets are provided along with a baseline attacker system. Participants shall develop their attacker systems in the form of automatic speaker verification systems and submit their scores on the development and evaluation data to the organizers. To do so, they can use any additional training data and models, provided that they are openly available and declared before the specified deadline. The metric for evaluation is equal error rate (EER). Results will be presented at the ICASSP 2025 special session to which 5 selected top-ranked participants will be invited to submit and present their challenge systems.
Please find more information in The First VoicePrivacy Attacker Challenge Evaluation Plan: https://www.voiceprivacychallenge.org/attacker/docs/Attacker_Challenge_Eval_Plan.pdf
Registration: https://t.co/pPEXxHEtP6
Contact: attacker.challenge@inria.fr
The VoicePrivacy Attacker Challenge Organizers: Xiaoxiao Miao - Singapore Institute of Technology, Singapore Natalia Tomashenko - Inria, France Emmanuel Vincent - Inria, France Junichi Yamagishi - NII, Japan
|
