Speech features for telemonitoring of Parkinson's disease symptoms

Abstract

The aim of this paper is tracking Parkinson's disease (PD) progression based on its symptoms on vocal system using Unified Parkinsons Disease Rating Scale (UPDRS). We utilize a standard speech signal feature set, which contains 6373 static features as functionals of low-level descriptor (LLD) contours, and select the most informative ones using the maximal relevance and minimal redundancy based on correlations (mRMR) criteria. Then, we evaluate performance of Gaussian mixture regression (GMR) and support vector regression (SVR) on estimating the third subscale of UPDRS, i.e., UPDRS: motor subscale (UPDRS-III). Among the most informative features, a list of features are selected after redundancy reduction. The selected features depict that LLDs providing information about spectrum flatness, spectral distribution of energy, and hoarseness of voice are the most important ones for estimating UPDRS-III. Moreover, the most informative statistical functions are related to range, maximum, minimum and standard deviation of LLDs, which is an evidence of the muscle weakness due to the PD. Furthermore, GMR outperforms SVR on compact feature sets while the performance of SVR improves by increasing number of features.

Things to Consider When Automatically Detecting Parkinson’s Disease Using the Phonation of Sustained Vowels: Analysis of Methodological Issues

“…It is uncommon to find studies which employ different corpora in model training and testing (cross-corpora validation) [22]. In some cases, the authors do not use cross-validation, and divide the corpus into training and testing subsets randomly [14,[22][23][24][25][26]. This increases the uncertainty of the results when using small corpora (usually no more than 3 h of recordings), as the testing partition is not large enough to be considered representative.…”

Hands–feet wireless devices: Test–retest reliability and discriminant validity of motor measures in Parkinson's disease telemonitoring

“…Second, information on other clinical aspects of PD (e.g., speech, facial expressions, rigidity, freezing, postural instability) was lacking, for which other tools have already been developed or are being tested. [34][35][36][37][38][39][40][41] In conclusion, the motor measures identified in this study are very reliable as they are highly discriminating (patients with PD vs. HC) and have high test-retest ICC values. In the near future, these parameters could be used for research purposes in telemonitoring tests for patients with PD.…”

“…First, the study had a relatively small sample size, and only right‐handed participants were included; this will be amended during the extension of the study in a much larger sample. Second, information on other clinical aspects of PD (e.g., speech, facial expressions, rigidity, freezing, postural instability) was lacking, for which other tools have already been developed or are being tested 34–41 …”

Dysarthric speech classification from coded telephone speech using glottal features

“…Objective speech-based assessment is economical and reliable, and it can be used to perform the diagnosis on a regular basis [6]. As speech-based diagnosis can be performed remotely, away from the hospital, it can in principle be conducted using a telemonitoring application [7]. In order to use speech-based diagnosis systems in telemonitoring applications, the system should be capable of handling varying speech degradation conditions, for example, coding (i.e., generation of quantization noise), transmission errors, band-pass filtering, and varying background environments.…”