Prototype-Based Disentanglement for Controllable Dysarthric Speech Synthesis
This work addresses the challenge of high variability and limited labeled data in dysarthric speech for assistive speech technologies, representing an incremental improvement over existing methods.
The paper tackles the problem of disentangling speaker identity and pathological articulation in dysarthric speech synthesis to improve controllability and robustness, resulting in bidirectional transformation between healthy and dysarthric speech with consistent ASR performance gains.
Dysarthric speech exhibits high variability and limited labeled data, posing major challenges for both automatic speech recognition (ASR) and assistive speech technologies. Existing approaches rely on synthetic data augmentation or speech reconstruction, yet often entangle speaker identity with pathological articulation, limiting controllability and robustness. In this paper, we propose ProtoDisent-TTS, a prototype-based disentanglement TTS framework built on a pre-trained text-to-speech backbone that factorizes speaker timbre and dysarthric articulation within a unified latent space. A pathology prototype codebook provides interpretable and controllable representations of healthy and dysarthric speech patterns, while a dual-classifier objective with a gradient reversal layer enforces invariance of speaker embeddings to pathological attributes. Experiments on the TORGO dataset demonstrate that this design enables bidirectional transformation between healthy and dysarthric speech, leading to consistent ASR performance gains and robust, speaker-aware speech reconstruction.