On the Relevance of Clinical Assessment Tasks for the Automatic Detection of Parkinson's Disease Medication State from Speech

TL;DR

This study demonstrates that self-supervised speech representations, especially prosody and continuous speech, effectively identify Parkinson's medication states, surpassing traditional methods and aiding clinical monitoring.

Contribution

Introduces a novel speaker-independent approach using self-supervised speech representations for Parkinson's medication state detection from speech.

Findings

Self-supervised speech features outperform knowledge-based descriptors.

Prosody and continuous speech are key indicators for medication state.

Achieved an F1-score of 88.2% in classification accuracy.

Abstract

The automatic identification of medication states of Parkinson's disease (PD) patients can assist clinicians in monitoring and scheduling personalized treatments, as well as studying the effects of medication in alleviating the motor symptoms that characterize the disease. This paper explores speech as a non-invasive and accessible biomarker for identifying PD medication states, introducing a novel approach that addresses this task from a speaker-independent perspective. While traditional machine learning models achieve competitive results, self-supervised speech representations prove essential for optimal performance, significantly surpassing knowledge-based acoustic descriptors. Experiments across diverse speech assessment tasks highlight the relevance of prosody and continuous speech in distinguishing medication states, reaching an F1-score of 88.2%. These findings may streamline clinicians' work and reduce patient effort in voice recordings.