We are pleased to announce the launch of the first COG-MHEAR Audio-visual Speech Enhancement Challenge (AVSEC)
Participants will work on a large dataset derived from TED talks to enhance speech in extremely challenging noisy environments and with competing speakers. The performance will be evaluated using human listening tests as well as with objective measures. We hope that the Challenge will create a benchmark for AVSEC research that will be useful for years to come. The challenge data and development tools are now available
AVSEC has been accepted as an official challenge at the IEEE Spoken Language Technology (SLT) Workshop to be held in Doha, Qatar, 9-12 Jan 2023, where a special session will be run.
for more details see the challenge website: link and our github repository: link
- You can now read more about our research in this blog link and in our annual report link
- Our first industry-focused workshop took place on June 24th 2021 with Sonova
- The project officially started on 1st March 2021