We are currently running a 2nd edition of the COG-MHEAR Audio-Visual Speech Enhancement Challenge (AVSEC-2):
https://challenge.cogmhear.org/ AVSEC sets the first benchmark in the field of audio-visual speech enhancement, providing a carefully designed dataset and scalable protocol
for human listening evaluation of AV-SE systems. We expect the challenge to bring together interdisciplinary research teams to advance the field of AV-SE and to provide further insight about the scope and limitations of current AV-SE approaches. Results and further information about the 1st edition can be found here: AVSEC-2 will be part of ASRU Special Sessions:
http://www.asru2023.org/ --- Timeline --- The proposed timeline is as follows: 1st February 2023: Release of training and development data. 15th-18th of May 2023: Release of baseline system. 15th-18th of May 2023: Evaluation data release. 22nd of May 2023: Leaderboard open for submissions. 3rd July 2023: Submission deadline for evaluation; ASRU paper submission deadline. 10th July 2023: ASRU Paper revision deadline August/September 2023: Evaluation with human participants. 15th September 2023: Early results release 30th September 2023: ASRU camera ready submission deadline. 16th-20th December 2023: ASRU 2023. We invite you to download the datasets and to take part in this new edition of the challenge. Best regards Dorothy Dr. Dorothy Hardy
(She/her) Research Fellow and Research Programme Manager COG-MHEAR research programme: Future Hearing Technology Edinburgh Napier University, UK Email:
D.Hardy@xxxxxxxxxxxx Office hours: Mon, Tue, Thur 10.30 – 16.30; Wed 14.00 – 16.30
|