Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
| Type of publication: | Conference paper |
| Citation: | ElHajal_INTERSPEECH2025_2025 |
| Publication status: | Accepted |
| Booktitle: | Proceedings of Interspeech |
| Year: | 2025 |
| Month: | August |
| Publisher: | ISCA |
| Location: | Rotterdam, Netherlands |
| URL: | https://arxiv.org/abs/2506.016... |
| Abstract: | Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiments on the Torgo corpus reveal that LF-MMI achieves significant word error rate reductions, especially for more severe cases of dysarthria, while fine-tuning Whisper on converted data has minimal effect on its performance. These results highlight the potential of unsupervised rhythm and voice conversion for dysarthric ASR. Code available at: https://github.com/idiap/RnV. |
| Keywords: | |
| Projects: |
PaSS IICT EMIL |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
