Publication detail

Acoustic analysis of poem recitation for identification of hypokinetic dysarthria in Parkinson’s disease patients

MUCHA, J. GALÁŽ, Z. KISKA, T. MEKYSKA, J. ZVONČÁK, V. SMÉKAL, Z.

Original Title

Acoustic analysis of poem recitation for identification of hypokinetic dysarthria in Parkinson’s disease patients

English Title

Acoustic analysis of poem recitation for identification of hypokinetic dysarthria in Parkinson’s disease patients

Type

abstract

Language

en

Original Abstract

Parkinson's disease (PD) is the second most frequent neurodegenerative disorder. Up to 90 % of PD patients suffer from speech disorder called hypokinetic dysarthria (HD). The goal of this work was to perform quantitative acoustic analysis of poem recitation in order to identify presence of HD. We employed conventional acoustic features to quantify specific HD disorders such as articulation, prosody, speech fluency and quality. It was observed that there is only mildly strong correlation between these speech features and diagnosis of the speakers. Next, we performed an univariate classification with these results of sensitivity in specific HD domains: imprecise articulation (62.63 %), dysprosody (61.62 %), speech dysfluency (71.72 %), and speech quality deterioration (59.60 %). The classification performance was improved by a multivariate classification, where we achieved sensitivity of 83.42 % using only two features describing imprecise articulation and speech quality deterioration in HD. Promising potential of the selected speech features and especially the use of poem recitation task to quantify and identify HD in PD was demonstrated.

English abstract

Parkinson's disease (PD) is the second most frequent neurodegenerative disorder. Up to 90 % of PD patients suffer from speech disorder called hypokinetic dysarthria (HD). The goal of this work was to perform quantitative acoustic analysis of poem recitation in order to identify presence of HD. We employed conventional acoustic features to quantify specific HD disorders such as articulation, prosody, speech fluency and quality. It was observed that there is only mildly strong correlation between these speech features and diagnosis of the speakers. Next, we performed an univariate classification with these results of sensitivity in specific HD domains: imprecise articulation (62.63 %), dysprosody (61.62 %), speech dysfluency (71.72 %), and speech quality deterioration (59.60 %). The classification performance was improved by a multivariate classification, where we achieved sensitivity of 83.42 % using only two features describing imprecise articulation and speech quality deterioration in HD. Promising potential of the selected speech features and especially the use of poem recitation task to quantify and identify HD in PD was demonstrated.

Keywords

poem recitation, acoustic analysis, binary classification, Parkinson’s disease, hypokinetic dysarthria

Released

20.04.2017

Publisher

Masarykova univerzita

Location

Brno

ISBN

978-80-210-8550-3

Book

Book of Abstracts, CEITEC PhD Retreat II

Pages from

47

Pages to

47

Pages count

1

BibTex


@misc{BUT135630,
  author="Ján {Mucha} and Zoltán {Galáž} and Tomáš {Kiska} and Jiří {Mekyska} and Vojtěch {Zvončák} and Zdeněk {Smékal}",
  title="Acoustic analysis of poem recitation for identification of hypokinetic dysarthria in Parkinson’s disease patients",
  annote="Parkinson's disease (PD) is the second most frequent neurodegenerative disorder. Up to 90 % of PD patients suffer from speech disorder called hypokinetic dysarthria (HD). The goal of this work was to perform quantitative acoustic analysis of poem recitation in order to identify presence of HD. We employed conventional acoustic features to quantify specific HD disorders such as articulation, prosody, speech fluency and quality. It was observed that there is only mildly strong correlation between these speech features and diagnosis of the speakers. Next, we performed an univariate classification with these results of sensitivity in specific HD domains: imprecise articulation (62.63 %), dysprosody (61.62 %), speech dysfluency (71.72 %), and speech quality deterioration (59.60 %). The classification performance was improved by a multivariate classification, where we achieved sensitivity of 83.42 % using only two features describing imprecise articulation and speech quality deterioration in HD. Promising potential of the selected speech features and especially the use of poem recitation task to quantify and identify HD in PD was demonstrated.",
  address="Masarykova univerzita",
  booktitle="Book of Abstracts, CEITEC PhD Retreat II",
  chapter="135630",
  howpublished="print",
  institution="Masarykova univerzita",
  year="2017",
  month="april",
  pages="47",
  publisher="Masarykova univerzita",
  type="abstract"
}