End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection.
Yuki TakashimaYusuke FujitaShinji WatanabeShota HoriguchiPaola GarcíaKenji NagamatsuPublished in: SLT (2021)
Keyphrases
- end to end
- speaker diarization
- speech recognition
- audio stream
- text localization and recognition
- broadcast news
- admission control
- congestion control
- speech activity detection
- automatic speech recognition
- application layer
- speaker identification
- pattern recognition
- speech signal
- noisy environments
- speaker verification