RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909756660121600 |
|---|---|
| author | Zhong, Terry Yi Tejedor-Garcia, Cristian Larson, Martha Bloem, Bastiaan R. |
| author_facet | Zhong, Terry Yi Tejedor-Garcia, Cristian Larson, Martha Bloem, Bastiaan R. |
| contents | Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representations. RECA-PD matches state-of-the-art performance in Speech-based PD detection while providing explanations that are more consistent and more clinically meaningful. Additionally, we demonstrate that performance degradation in certain speech tasks (e.g., monologue) can be mitigated by segmenting long recordings. Our findings indicate that performance and explainability are not necessarily mutually exclusive. Future work will enhance the usability of explanations for non-experts and explore severity estimation to increase the real-world clinical relevance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification Zhong, Terry Yi Tejedor-Garcia, Cristian Larson, Martha Bloem, Bastiaan R. Sound Artificial Intelligence Computation and Language Audio and Speech Processing Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representations. RECA-PD matches state-of-the-art performance in Speech-based PD detection while providing explanations that are more consistent and more clinically meaningful. Additionally, we demonstrate that performance degradation in certain speech tasks (e.g., monologue) can be mitigated by segmenting long recordings. Our findings indicate that performance and explainability are not necessarily mutually exclusive. Future work will enhance the usability of explanations for non-experts and explore severity estimation to increase the real-world clinical relevance. |
| title | RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification |
| topic | Sound Artificial Intelligence Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.03594 |