RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification

2025/07/04 by Zhong, Terry Yi, Tejedor-Garcia, Cristian, Larson, Martha +1
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2507.03594

Abstract

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.

Citations

• Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers
• A Survey on Human-Centered Evaluation of Explainable AI Methods in Clinical Decision Support Systems
• Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
• Speech as a Biomarker for Disease Detection
• Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
• Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions
• CAT: Cross Attention in Vision Transformer
• Neural Additive Models: Interpretable Machine Learning with Neural Nets
• Cross Attention Network for Few-shot Classification
• Attention-Based Models for Speech Recognition
• Neural Machine Translation by Jointly Learning to Align and Translate

Related

• Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
• Interpretable Early Detection of Parkinson's Disease through Speech Analysis
• Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis
• A novel fusion architecture for detecting Parkinson’s Disease using semi-supervised speech embeddings
• A Novel Fusion Architecture for PD Detection Using Semi-Supervised Speech Embeddings