Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings

TLDR

Interest has grown in using Parkinsonism speech pattern analysis to develop predictive telediagnosis and telemonitoring models. The study seeks to collect diverse voice samples and evaluate whether sample type predicts Parkinson’s disease and whether central tendency and dispersion metrics adequately represent subjects. Researchers compiled sustained vowels, words, and sentences from speaking exercises of Parkinson’s patients to create a multi‑type speech dataset. Sustained vowels provide the strongest PD‑discriminative signals, and summarizing each subject’s recordings with central tendency and dispersion metrics improves predictive model generalization.

Abstract

There has been an increased interest in speech pattern analysis applications of Parkinsonism for building predictive telediagnosis and telemonitoring models. For this purpose, we have collected a wide variety of voice samples, including sustained vowels, words, and sentences compiled from a set of speaking exercises for people with Parkinson's disease. There are two main issues in learning from such a dataset that consists of multiple speech recordings per subject: 1) How predictive these various types, e.g., sustained vowels versus words, of voice samples are in Parkinson's disease (PD) diagnosis? 2) How well the central tendency and dispersion metrics serve as representatives of all sample recordings of a subject? In this paper, investigating our Parkinson dataset using well-known machine learning tools, as reported in the literature, sustained vowels are found to carry more PD-discriminative information. We have also found that rather than using each voice recording of each subject as an independent data sample, representing the samples of a subject with central tendency and dispersion metrics improves generalization of the predictive model.