Automatic detection of voice onset time in dysarthric speech
Michal Novotny, Jakub Pospisil, Roman Cmejla, Jan Rusz
Abstract
Although a number of speech disorders reflect varying involvement of brain areas, recently published automatic speech analyses have primarily been limited to hypokinetic dysarthria in Parkinson's disease (PD). Therefore, the aim of the present study was to provide an automatic algorithm suitable for the assessment of voice onset time (VOT) in various dysarthria types. Twenty-four PD participants with hypokinetic dysarthria and 40 Huntington's disease (HD) subjects with hyperkinetic dysarthria were included. These two types of dysarthria were selected in the design of a robust algorithm as they contain most of the dysarthric patterns found among all dysarthria subtypes. For a 10 ms threshold, the proposed algorithm reached approximately 90% accuracy in PD speakers and 80% accuracy in HD speakers. The accuracy of 80% obtained in HD was superior to the performance of 55% achieved by a previous algorithm designed particularly for hypokinetic dysarthria in PD.
BibTeX
@inproceedings{icassp2015_automaticdetecti,
title = {Automatic detection of voice onset time in dysarthric speech},
author = {Michal Novotny and Jakub Pospisil and Roman Cmejla and Jan Rusz},
booktitle = {ICASSP 2015},
year = {2015}
}