Fine-tuning Whisper on over 100 hours of personalized dysarthric speech data reduces WER to 9.7% for a single speaker.
Improved dysarthric speech to text conversion via TTS personalization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adapting Foundation ASR Models to Dysarthric Speech: A Case Study
Fine-tuning Whisper on over 100 hours of personalized dysarthric speech data reduces WER to 9.7% for a single speaker.