Latest Updates: 

  • Our next annual review takes place on 14th March 2023. Contact us using link for more details

  • Join our user group using using link to find our more about our research and to give your opinions. We host both online and in-person events to gain feedback on our research.

  • We have launched the first COG-MHEAR Audio-visual Speech Enhancement Challenge (AVSEC). Participants worked on a large dataset derived from TED talks to enhance speech in extremely challenging noisy environments and with competing speakers. 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: the challenge website: link and our github repository: link

  • You can now read more about our research in this blog link
  • Our first industry-focused workshop took place on June 24th 2021 with Sonova
  • The project officially started on 1st March 2021