|
Call for papers:
2024 Interspeech Satellite Workshop: Audio-Visual Speech Enhancement Challenge (AVSEC-3) & IEEE JSTSP Special Issue
Dear all (with apologies for any cross-postings)
We are running the third international edition of the audio-visual speech enhancement (AVSEC-3) as a Satellite Workshop of Interspeech 2024 in Kos, Greece, on 1st September (http://challenge.cogmhear.org)
The Audio-Visual Speech Enhancement Challenge (AVSEC) sets the first benchmark in the field, providing a common framework for the evaluation of audio-visual speech enhancement and separation systems. The evaluation protocol consists of listening tests with
human participants. Building upon two successful editions of the Challenge (IEEE SLT 2022 and ASRU 2023), we expect the third edition to further advance system performance. Additionally, AVSEC-3 will serve as a networking and collaborative platform for participants
to reflect on the scope, limitations, and challenges in designing and evaluating audio-visual speech and hearing technologies.
To register for the challenge please follow the guidelines on the website:
Challenge datasets:
https://challenge.cogmhear.org/#/challenge-data/data-spec
Important Dates:
We invite prospective authors to submit either 2-page extended abstracts or full-length papers of 4-6 pages following the INTERSPEECH 2024 paper template. All accepted papers will be published in ISCA Proceedings.
We welcome submissions from participants of both the second (AVSEC-2) and third editions (AVSEC-3) of the Challenge and also invite submissions on related research topics, including but not limited to the following:
- Low-latency approaches to audio-visual speech enhancement and separation.
- Human auditory-inspired models of multi-modal speech perception and enhancement.
- Energy-efficient audio-visual speech enhancement and separation methods.
- Machine learning for diverse target listeners and diverse listening scenarios.
- Audio quality and intelligibility assessment of audio-visual speech enhancement systems.
- Objective metrics to predict quality and intelligibility from audio-visual stimuli.
- Understanding human speech perception in competing speaker scenarios.
- Clinical applications and live demonstrators of audio-visual speech enhancement and separation, (e.g. multi-modal hearing assistive technologies for hearing-impaired listeners; speech-enabled communication aids to support autistic people with speech disorders).
- Accessibility and human-centric factors in the design and evaluation of innovative multimodal technologies, including multi-modal corpus development, public perceptions, ethics considerations, standards, societal, economic and political impacts.
IEEE JSTSP Special Issue
Authors of selected AVSEC-3 Workshop papers (including winners and runner-ups of each Challenge Track) will be invited to submit significantly extended papers for consideration in a Special Issue of the IEEE Journal of Selected Topics in Signal Processing (JSTSP)
on "Deep Multimodal Speech Enhancement and Separation" - CFP available below and here:
https://signalprocessingsociety.org/publications-resources/special-issue-deadlines/ieee-jstsp-special-issue-deep-multimodal-speech-enhancement-and-separation -
full manuscript submission deadline: 30 Sep 2024)
Workshop registration:
Workshop registration costs:
Further information about the workshop registration process will be made available soon through the Challenge website and mailing list.
We look forward to seeing you in Kos.
AVSEC Organising Team
--
Professor Amir Hussain
School of Computing, Engineering & The Built Environment
Edinburgh Napier University, Edinburgh EH10 5DT, UK
E-mail: a.hussain@xxxxxxxxxxxx
|