Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917895491026944 |
|---|---|
| author | Hajal, Karl El Hermann, Enno Kulkarni, Ajinkya -Doss, Mathew Magimai. |
| author_facet | Hajal, Karl El Hermann, Enno Kulkarni, Ajinkya -Doss, Mathew Magimai. |
| contents | Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcribed speech data to estimate speaking rates and phoneme durations, which might not be available for unseen speakers. Therefore, we combine unsupervised rhythm and voice conversion methods based on self-supervised speech representations to map dysarthric to typical speech. We evaluate the outputs with a large ASR model pre-trained on healthy speech without further fine-tuning and find that the proposed rhythm conversion especially improves performance for speakers of the Torgo corpus with more severe cases of dysarthria. Code and audio samples are available at https://idiap.github.io/RnV . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR Hajal, Karl El Hermann, Enno Kulkarni, Ajinkya -Doss, Mathew Magimai. Audio and Speech Processing Artificial Intelligence Machine Learning Sound Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcribed speech data to estimate speaking rates and phoneme durations, which might not be available for unseen speakers. Therefore, we combine unsupervised rhythm and voice conversion methods based on self-supervised speech representations to map dysarthric to typical speech. We evaluate the outputs with a large ASR model pre-trained on healthy speech without further fine-tuning and find that the proposed rhythm conversion especially improves performance for speakers of the Torgo corpus with more severe cases of dysarthria. Code and audio samples are available at https://idiap.github.io/RnV . |
| title | Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound |
| url | https://arxiv.org/abs/2501.10256 |