Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.01369 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918365637902336 |
|---|---|
| author | Wu, Minghui Liu, Xueling Fan, Jiahuan Tang, Haitao Zhang, Yanyong Zhang, Yue |
| author_facet | Wu, Minghui Liu, Xueling Fan, Jiahuan Tang, Haitao Zhang, Yanyong Zhang, Yue |
| contents | Dysarthric speech exhibits abnormal prosody and significant speaker variability, presenting persistent challenges for automatic speech recognition (ASR). While text-to-speech (TTS)-based data augmentation has shown potential, existing methods often fail to accurately model the pathological rhythm and acoustic style of dysarthric speech. To address this, we propose DARS, a dysarthria-aware rhythm-style synthesis framework based on the Matcha-TTS architecture. DARS incorporates a multi-stage rhythm predictor optimized by contrastive preferences between normal and dysarthric speech, along with a dysarthric-style conditional flow matching mechanism, jointly enhancing temporal rhythm reconstruction and pathological acoustic style simulation. Experiments on the TORGO dataset demonstrate that DARS achieves a Mean Cepstral Distortion (MCD) of 4.29, closely approximating real dysarthric speech. Adapting a Whisper-based ASR system with synthetic dysarthric speech from DARS achieves a 54.22% relative reduction in word error rate (WER) compared to state-of-the-art methods, demonstrating the framework's effectiveness in enhancing recognition performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01369 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement Wu, Minghui Liu, Xueling Fan, Jiahuan Tang, Haitao Zhang, Yanyong Zhang, Yue Sound Computation and Language Dysarthric speech exhibits abnormal prosody and significant speaker variability, presenting persistent challenges for automatic speech recognition (ASR). While text-to-speech (TTS)-based data augmentation has shown potential, existing methods often fail to accurately model the pathological rhythm and acoustic style of dysarthric speech. To address this, we propose DARS, a dysarthria-aware rhythm-style synthesis framework based on the Matcha-TTS architecture. DARS incorporates a multi-stage rhythm predictor optimized by contrastive preferences between normal and dysarthric speech, along with a dysarthric-style conditional flow matching mechanism, jointly enhancing temporal rhythm reconstruction and pathological acoustic style simulation. Experiments on the TORGO dataset demonstrate that DARS achieves a Mean Cepstral Distortion (MCD) of 4.29, closely approximating real dysarthric speech. Adapting a Whisper-based ASR system with synthetic dysarthric speech from DARS achieves a 54.22% relative reduction in word error rate (WER) compared to state-of-the-art methods, demonstrating the framework's effectiveness in enhancing recognition performance. |
| title | DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement |
| topic | Sound Computation and Language |
| url | https://arxiv.org/abs/2603.01369 |