Diarization-conditioned Whisper with frame-level transforms and query-key biasing achieves strong target-speaker ASR on AMI, NOTSOFAR-1, Libri2Mix, and LibriCSS.
Li, et al., Recent advances in end-to-end automatic speech recogni- tion, APSIPA Transactions on Signal and Information Processing 11 (1) (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition
Diarization-conditioned Whisper with frame-level transforms and query-key biasing achieves strong target-speaker ASR on AMI, NOTSOFAR-1, Libri2Mix, and LibriCSS.