Latest Updates: 

  • You are warmly invited to submit papers to IEEE JSTSP Special Issue on Deep Multimodal Speech Enhancement and Separation. The submission deadline is: 30 September 2024

  • Congratulations to COG-MHEAR's senior postdoctoral research fellow, Dr Mandar Gogate for winning first prize at the 2022 AVSEC-1 Challenge. He received a £250 Amazon gift voucher along with a winner certificate at the COG-MHEAR Industry Workshop organized with Sonova at ENU Craiglockart Campus, on 15-16 August 2023

  • You are warmly invited to submit papers to a special issue of IEEE Transactions on AI entitled 'Conversational AI'. Areas of interest include speech based multi-modal processing for conversational AI, amongst many topics listed in the attached document. The submission deadline is 30th September 2023.

  • Call for contributions and participation at the 2023 Audiomostly Conference being organised at Edinburgh Napier University from 30 Aug - 2 Sep 2023. For more information see:

    Audiomostly is an interdisciplinary conference on design and experience of interaction with sound that prides itself on embracing applied theory and reflective practice. Its annual gatherings bring together thinkers and doers from academia and industry that share an interest in sonic interaction and the use of audio for interface design. This remit covers product design, auditory display, computer games and virtual environments, new musical instruments, and education and workplace tools. It further includes fields such as the psychology of sound and music, cultural studies, system engineering, and everything in between in which sonic interaction plays a role)
  • We are currently running a 2nd edition of the COG-MHEAR Audio-Visual Speech Enhancement Challenge (AVSEC-2): link

    We invite you to download the datasets and to take part in this new edition of the challenge. The deadline for entries has been extended to 17th July 2023.
    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.

  • The Cabaret of Dangerous Ideas is a great way to find out about developments in research. It is part of the Edinburgh Fringe Festival. Book now for ‘Hearing Aids Don’t Work’: Two stand-up comedy shows on the 9th and 14th August: link

  • Join our user group 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 are particularly keen to recruit hearing aid users in Scotland's central belt.
    Our next user workshop will take place in Edinburgh on Wednesday 8th November 2023. Get in touch to join in: link
  • You can read more about our research in this blog link
  • Our first industry-focused workshop took place on June 24th 2021 with Sonova. Exciting developments have followed. Join our user group to be the first to find out about new demonstration software and hardware: link
  • The project officially started on 1st March 2021