MSA-ASR freezes Whisper, trains a speaker module with weak TitaNet-L embeddings and an embedding-alignment loss, and shows competitive cpWER on several SA-ASR benchmarks while degrading at high overlap.
Integration of speech separation, diarization, and recognition for multi-speaker meetings: System de- scription, comparison, and analysis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models
MSA-ASR freezes Whisper, trains a speaker module with weak TitaNet-L embeddings and an embedding-alignment loss, and shows competitive cpWER on several SA-ASR benchmarks while degrading at high overlap.