Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2408.12279 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911999479250944 |
|---|---|
| author | Dang, Shaoxiang Matsumoto, Tetsuya Takeuchi, Yoshinori Tsuboi, Takashi Tanaka, Yasuhiro Nakatsubo, Daisuke Maesawa, Satoshi Saito, Ryuta Katsuno, Masahisa Kudo, Hiroaki |
| author_facet | Dang, Shaoxiang Matsumoto, Tetsuya Takeuchi, Yoshinori Tsuboi, Takashi Tanaka, Yasuhiro Nakatsubo, Daisuke Maesawa, Satoshi Saito, Ryuta Katsuno, Masahisa Kudo, Hiroaki |
| contents | The potential of deep learning in clinical speech processing is immense, yet the hurdles of limited and imbalanced clinical data samples loom large. This article addresses these challenges by showcasing the utilization of automatic speech recognition and self-supervised learning representations, pre-trained on extensive datasets of normal speech. This innovative approach aims to estimate voice quality of patients with impaired vocal systems. Experiments involve checks on PVQD dataset, covering various causes of vocal system damage in English, and a Japanese dataset focusing on patients with Parkinson's disease before and after undergoing subthalamic nucleus deep brain stimulation (STN-DBS) surgery. The results on PVQD reveal a notable correlation (>0.8 on PCC) and an extraordinary accuracy (<0.5 on MSE) in predicting Grade, Breathy, and Asthenic indicators. Meanwhile, progress has been achieved in predicting the voice quality of patients in the context of STN-DBS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12279 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Developing vocal system impaired patient-aimed voice quality assessment approach using ASR representation-included multiple features Dang, Shaoxiang Matsumoto, Tetsuya Takeuchi, Yoshinori Tsuboi, Takashi Tanaka, Yasuhiro Nakatsubo, Daisuke Maesawa, Satoshi Saito, Ryuta Katsuno, Masahisa Kudo, Hiroaki Sound Artificial Intelligence Audio and Speech Processing The potential of deep learning in clinical speech processing is immense, yet the hurdles of limited and imbalanced clinical data samples loom large. This article addresses these challenges by showcasing the utilization of automatic speech recognition and self-supervised learning representations, pre-trained on extensive datasets of normal speech. This innovative approach aims to estimate voice quality of patients with impaired vocal systems. Experiments involve checks on PVQD dataset, covering various causes of vocal system damage in English, and a Japanese dataset focusing on patients with Parkinson's disease before and after undergoing subthalamic nucleus deep brain stimulation (STN-DBS) surgery. The results on PVQD reveal a notable correlation (>0.8 on PCC) and an extraordinary accuracy (<0.5 on MSE) in predicting Grade, Breathy, and Asthenic indicators. Meanwhile, progress has been achieved in predicting the voice quality of patients in the context of STN-DBS. |
| title | Developing vocal system impaired patient-aimed voice quality assessment approach using ASR representation-included multiple features |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.12279 |