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

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.

A Study on the Diagnosis of Parkinson’s Disease using Digitized Wacom Graphics Tablet Dataset

“…Stability Test on Certain Point (STCP): There is a certain red point in the middle of the screen and the subjects are asked to hold the digital pen on the point without touching the screen in a certain time in this test. The purpose of this test is to determine the patient's hand stability or hand tremor level [8,20].…”

“…Spiral drawing is used in assessing of tremor severity for the clinical evaluation of medical treatments [7]. Sakar et al [8] collected a wide range of voice samples for building predictive telediagnosis and telemonitoring models. They investigated more PD-discriminative information, using well-known machine learning tools and published the dataset for researchers.…”

Pathological Voice Signal Analysis Using Machine Learning Based Approaches

“…The PD dataset consists of a range of voice signal measurements from 41 patients with PD and 52 healthy individuals who were recruited at the Department of Neurology in Cerrahpasa Faculty of Medicine, Istanbul University (Sakar et al, 2013). Multiple speech recordings of each patient is gathered and stored.…”

“…Multiple speech recordings of each patient is gathered and stored. From all subjects, 26 a wide variety of voice samples, including number from 1 to 10, nine words, four short sentences, and sustained vowels "a", "o", and "u" were recorded (Sakar et al, 2013).…”

Voice Parameter Analysis for the disease detection

“…Voice analysis can be done either in the time domain or in the frequency domain. The time domain waveform of voice signal carries all the auditory information like phonemes, syllables, prosody levels, etc [3] while the frequency domain represents the spectral characteristics of the voice signal such as frequency, pitch, etc. Table 1 illustrates information that can be extracted from voice parameters by time-frequency-based analysis.…”