Towards Improving End-to-End Neural Diarization
- đ¤ Speaker: Dr Federico Landini, Brno University of Technology
- đ Date & Time: Tuesday 06 August 2024, 12:00 - 13:00
- đ Venue: Hybrid: JDB Seminar Room, Engineering Department or Zoom: https://cam-ac-uk.zoom.us/j/88498768580?pwd=1zjqKCU8AiRcd7ZR6SXBTjc0ScElsc.1
Abstract
Until recently, diarization systems were formed by different submodules like voice activity detection, embedding extraction and clustering of such embeddings. However, the last quinquennial has seen many developments in diarization towards end-to-end models. These models, unlike modular ones, are trained to optimize a diarization-related loss and provide a more straightforward inference. Nevertheless, end-to-end systems still 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.
Series This talk is part of the CUED Speech Group Seminars series.
Included in Lists
- Cambridge Forum of Science and Humanities
- Cambridge Language Sciences
- Cambridge talks
- Chris Davis' list
- CUED Speech Group Seminars
- Guy Emerson's list
- Hybrid: JDB Seminar Room, Engineering Department or Zoom: https://cam-ac-uk.zoom.us/j/88498768580?pwd=1zjqKCU8AiRcd7ZR6SXBTjc0ScElsc.1
- Information Engineering Division seminar list
- PhD related
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)


Tuesday 06 August 2024, 12:00-13:00