BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Improving End-to-End Neural Diarization - Dr Federico Land
 ini\, Brno University of Technology
DTSTART:20240806T110000Z
DTEND:20240806T120000Z
UID:TALK219421@talks.cam.ac.uk
CONTACT:Simon Webster McKnight
DESCRIPTION:Until recently\, diarization systems were formed by different 
 submodules like voice activity detection\, embedding extraction and cluste
 ring of such embeddings. However\, the last quinquennial has seen many dev
 elopments in diarization towards end-to-end models. These models\, unlike 
 modular ones\, are trained to optimize a diarization-related loss and prov
 ide a more straightforward inference. Nevertheless\, end-to-end systems st
 ill pose certain challenges. In this talk\, I will comment on some of the 
 work I did addressing some of their problems regarding synthetic training 
 data generation and handling variable numbers of speakers.
LOCATION:Hybrid: JDB Seminar Room\, Engineering Department or Zoom: https:
 //cam-ac-uk.zoom.us/j/88498768580?pwd=1zjqKCU8AiRcd7ZR6SXBTjc0ScElsc.1
END:VEVENT
END:VCALENDAR