Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation
A controllable dysarthric speech synthesis framework for ASR augmentation with separate prompt-derived timbre prefixes and learnable patient-specific pathology prefixes that provides effective speaker-diverse augmentation when combined with real data.
Hao-Shen Wang, Xuelin Zhong, Bing-Bing Lin et al.
· 0 citations