Continuous-Speech Parkinson's Disease Detection Using Acoustic and Inharmonicity Features

2026-06-17

AI Summary

This study addresses the limitations of traditional Parkinson’s disease (PD) detection methods that rely on sustained vowel phonation, which are ill-suited for real-world, natural speech scenarios. To bridge this gap, the work presents the first systematic exploration of using continuous speech for PD detection, introducing a novel modeling framework that integrates conventional acoustic features with a newly proposed inharmonicity-based feature set. The approach incorporates speaker-level evaluation and rigorous safeguards against data leakage. Experimental results on two public datasets demonstrate that models leveraging continuous speech significantly outperform those based on sustained vowels, with the inclusion of inharmonicity features further enhancing diagnostic performance. These findings underscore the potential of the proposed method to enable unobtrusive, continuous PD monitoring in everyday settings.

Abstract

Notable efforts have been made to identify Parkinson's disease (PD) from vocal data, primarily using sustained vowel phonations. In this work, we extend on these efforts introducing a PD identification approach for continuous speech, enabling a practical background monitoring of voice data to detect vocal changes indicative of PD. Using two distinct data sets, we compare the best sustained vowel model with that of the proposed continuous speech model, clearly illustrating the preferential performance of the latter. We examine approaches for speaker level evaluation and data leakage preventions, as well as how vowel information may be reliable extracted from continuous speech. The proposed method framework exploits both traditional acoustic representations and a promising novel inharmonicity based framework, showing how the latter provides complementary information improving the performance for one of the data sets; however, for the other data set, this information did not significantly improve (nor reduce) the performance, suggesting that further studies are required before being able to draw firm conclusions in its use. Overall, the work clearly illustrates the benefit of forming PD classification using continuous speech compared to using sustained vowel sounds.

Problem

• Parkinson's disease
• continuous speech
• vocal detection
• acoustic features
• inharmonicity

Innovation

• continuous speech
• inharmonicity
• Parkinson's disease detection
• acoustic features
• speaker-level evaluation