Whisper trained with realistic 'um'/'uh' labels generated by Gemini reached 5.5% WER on L2 English speech, an 11.3% relative improvement over training with hesitations removed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription Systems
Whisper trained with realistic 'um'/'uh' labels generated by Gemini reached 5.5% WER on L2 English speech, an 11.3% relative improvement over training with hesitations removed.