Combining x-vector speaker conditioning, AdaLoRA adapters, and Parler-TTS synthetic speech reduces word error rates for dysarthric ASR on the SAP development set.
SemScore is a weighted sum of BERTscore [49], phonetic distance, and natural language infer- ence probability [50]
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
-
Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
Combining x-vector speaker conditioning, AdaLoRA adapters, and Parler-TTS synthetic speech reduces word error rates for dysarthric ASR on the SAP development set.