Continuous-Speech Parkinson's Disease Detection Using Acoustic and Inharmonicity Features
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 reliably 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.
Related
- On Generalized Naive Bayes with Continuous Features
- ArborEnum: Decision Tree Rashomon Sets over Continuous Features
- Clinically Interpretable Biological Age Estimation Using CatBoost and SHAP with Continuous and Categorical Features from NHANES
- Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features
- Hydrodynamic limits for the Boltzmann-Fermi-Dirac equation: Acoustic and Stokes-Fourier
BibTeX
@misc{li2026continuousspeech,
title = {{Continuous-Speech Parkinson's Disease Detection Using Acoustic and Inharmonicity Features}},
author = {Rujia Li and Niloofar Momeni and Susanna Whitling and Andreas Jakobsson},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.19125},
eprint = {2606.19125},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.19125},
}
RIS
TY - UNPB
TI - Continuous-Speech Parkinson's Disease Detection Using Acoustic and Inharmonicity Features
AU - Rujia Li
AU - Niloofar Momeni
AU - Susanna Whitling
AU - Andreas Jakobsson
PY - 2026
DA - 2026/10/11
PB - arXiv
DO - 10.48550/arxiv.2606.19125
UR - https://arxiv.org/abs/2606.19125
AB - 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 reliably 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.
ER -