Publication detail

Analysis of phonation in patients with Parkinson's disease using empirical mode decomposition

SMÉKAL, Z. MEKYSKA, J. GALÁŽ, Z. MŽOUREK, Z. REKTOROVÁ, I. FAÚNDEZ ZANUY, M.

Original Title

Analysis of phonation in patients with Parkinson's disease using empirical mode decomposition

English Title

Analysis of phonation in patients with Parkinson's disease using empirical mode decomposition

Type

conference paper

Language

en

Original Abstract

This paper deals with an acoustic analysis of hypokinetic dysarthria in patients with Parkinson's disease (PD). The analysis is based on parametrization of five basic Czech vowels using conventional features and parameters based on empirical mode decomposition (EMD). Experimental dataset consists of 84 PD patients with different disease progress and 49 healthy controls. From the single-vowel-analysis point of view we observed that sustained vowels pronounced with minimum intensity (not whispering) outperformed the other vowels' realization (including the most popular sustained vowel [a] pronounced with normal intensity). Then we employed a classification along with feature selection and again obtained the best results in the case of silent sustained vowels (accuracy ACC = 84 %, sensitivity SEN = 86% and specificity SPE = 82 %). Finally we considered classification of PD using different vowels' realization and reached accuracy = 94 %, sensitivity = 96% and specificity = 90 %. Features based on EMD significantly improved the results.

English abstract

This paper deals with an acoustic analysis of hypokinetic dysarthria in patients with Parkinson's disease (PD). The analysis is based on parametrization of five basic Czech vowels using conventional features and parameters based on empirical mode decomposition (EMD). Experimental dataset consists of 84 PD patients with different disease progress and 49 healthy controls. From the single-vowel-analysis point of view we observed that sustained vowels pronounced with minimum intensity (not whispering) outperformed the other vowels' realization (including the most popular sustained vowel [a] pronounced with normal intensity). Then we employed a classification along with feature selection and again obtained the best results in the case of silent sustained vowels (accuracy ACC = 84 %, sensitivity SEN = 86% and specificity SPE = 82 %). Finally we considered classification of PD using different vowels' realization and reached accuracy = 94 %, sensitivity = 96% and specificity = 90 %. Features based on EMD significantly improved the results.

Keywords

Parkinson’s disease, hypokinetic dysarthria, speech analysis, empirical mode decomposition

RIV year

2015

Released

09.07.2015

ISBN

978-1-4673-7487-3

Book

2015 International Symposium on Signals, Circuits and Systems (ISSCS)

Pages from

1

Pages to

4

Pages count

4

URL

BibTex


@inproceedings{BUT115863,
  author="Zdeněk {Smékal} and Jiří {Mekyska} and Zoltán {Galáž} and Zdeněk {Mžourek} and Irena {Rektorová} and Marcos {Faúndez Zanuy}",
  title="Analysis of phonation in patients with Parkinson's disease using empirical mode decomposition",
  annote="This paper deals with an acoustic analysis of hypokinetic dysarthria in patients with Parkinson's disease (PD). The analysis is based on parametrization of five basic Czech vowels using conventional features and parameters based on empirical mode decomposition (EMD). Experimental dataset consists of 84 PD patients with different disease progress and 49 healthy controls. From the single-vowel-analysis point of view we observed that sustained vowels pronounced with minimum intensity (not whispering) outperformed the other vowels' realization (including the most popular sustained vowel [a] pronounced with normal intensity). Then we employed a classification along with feature selection and again obtained the best results in the case of silent sustained vowels (accuracy ACC = 84 %, sensitivity SEN = 86% and specificity SPE = 82 %). Finally we considered classification of PD using different vowels' realization and reached accuracy = 94 %, sensitivity = 96% and specificity = 90 %. Features based on EMD significantly improved the results.",
  booktitle="2015 International Symposium on Signals, Circuits and Systems (ISSCS)",
  chapter="115863",
  doi="10.1109/ISSCS.2015.7203931",
  howpublished="online",
  year="2015",
  month="july",
  pages="1--4",
  type="conference paper"
}