A hybrid VAD that merges frame-level VAD with Whisper timestamps, plus denoising as training augmentation, reduces diarization error to 17% for teacher-student speech in noisy classrooms.
These datasets provide ∼60 hours of speech recordings that reflect various classroom environments, speaker demographics, and noise conditions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Stage Speaker Diarization for Noisy Classrooms
A hybrid VAD that merges frame-level VAD with Whisper timestamps, plus denoising as training augmentation, reduces diarization error to 17% for teacher-student speech in noisy classrooms.