Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation

תקציר מקורי באנגליתarXiv:2602.08696v3 Announce Type: replace-cross Abstract: Dysarthric speech recognition is limited by high speaker variability and scarce labeled data. Existing synthesis methods often couple speaker identity with dysarthric articulation, reducing control over generated speech. We propose a controllable dysarthric speech synthesis framework for ASR augmentation with separate prompt-derived timbre prefixes and learnable patient-specific pathology prefixes. Built on a pre-trained neural codec language model adapted using LoRA, the framework combines both prefixes through additive conditioning. A dual-classifier objective with gradient reversal and voice-conversion-based counterfactual augmentation promotes factor separation, allowing learned pathology conditions to be paired with different t