Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909831642742784 |
|---|---|
| author | Plantinga, Peter Sattari, Roozbeh Marcotte, Karine Di Gironimo, Carla Sharp, Madeleine Bouvier, Liziane Geddes, Maiya Verduyckt, Ingrid de Villers-Sidani, Étienne Ravanelli, Mirco Klein, Denise |
| author_facet | Plantinga, Peter Sattari, Roozbeh Marcotte, Karine Di Gironimo, Carla Sharp, Madeleine Bouvier, Liziane Geddes, Maiya Verduyckt, Ingrid de Villers-Sidani, Étienne Ravanelli, Mirco Klein, Denise |
| contents | The speech of people with Parkinson's Disease (PD) has been shown to hold important clues about the presence and progression of the disease. We investigate the factors based on which humans experts make judgments of the presence of disease in speech samples over five different speech tasks: phonations, sentence repetition, reading, recall, and picture description. We make comparisons by conducting listening tests to determine clinicians accuracy at recognizing signs of PD from audio alone, and we conduct experiments with a machine learning system for detection based on Whisper. Across tasks, Whisper performs on par or better than human experts when only audio is available, especially on challenging but important subgroups of the data: younger patients, mild cases, and female patients. Whisper's ability to recognize acoustic cues in difficult cases complements the multimodal and contextual strengths of human experts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07299 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease Plantinga, Peter Sattari, Roozbeh Marcotte, Karine Di Gironimo, Carla Sharp, Madeleine Bouvier, Liziane Geddes, Maiya Verduyckt, Ingrid de Villers-Sidani, Étienne Ravanelli, Mirco Klein, Denise Audio and Speech Processing Sound The speech of people with Parkinson's Disease (PD) has been shown to hold important clues about the presence and progression of the disease. We investigate the factors based on which humans experts make judgments of the presence of disease in speech samples over five different speech tasks: phonations, sentence repetition, reading, recall, and picture description. We make comparisons by conducting listening tests to determine clinicians accuracy at recognizing signs of PD from audio alone, and we conduct experiments with a machine learning system for detection based on Whisper. Across tasks, Whisper performs on par or better than human experts when only audio is available, especially on challenging but important subgroups of the data: younger patients, mild cases, and female patients. Whisper's ability to recognize acoustic cues in difficult cases complements the multimodal and contextual strengths of human experts. |
| title | Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2510.07299 |