Publication detail

Acoustic Analysis of Sentences Complicated for Articulation in Patients with Parkinson's Disease

KISKA, T.

Original Title

Acoustic Analysis of Sentences Complicated for Articulation in Patients with Parkinson's Disease

English Title

Acoustic Analysis of Sentences Complicated for Articulation in Patients with Parkinson's Disease

Type

conference paper

Language

en

Original Abstract

This paper deals with acoustic analysis of hypokinetic dysarthria. Hypokinetic dysarthria is a speech motor dysfunction that is present in approximately 90% of patients with Parkinson’s disease (PD). The work is mainly focused on parameterization techniques that can be used to diagnose or monitor this disease as well as estimate its progress. Acoustic analysis can be used to estimate a grade of hypokinetic dysarthria in fields of phonation, articulation, prosody and speech fluency. Regarding the parameterization, new features based on RASTA method were proposed. The analysis is based on parametrization of sentences complicated for articulation. Experimental dataset consists of 101 PD patients with different disease progress and 53 healthy controls. For the purpose of feature selection we employed mRMR (minimum Redundancy Maximum Relevance) method.

English abstract

This paper deals with acoustic analysis of hypokinetic dysarthria. Hypokinetic dysarthria is a speech motor dysfunction that is present in approximately 90% of patients with Parkinson’s disease (PD). The work is mainly focused on parameterization techniques that can be used to diagnose or monitor this disease as well as estimate its progress. Acoustic analysis can be used to estimate a grade of hypokinetic dysarthria in fields of phonation, articulation, prosody and speech fluency. Regarding the parameterization, new features based on RASTA method were proposed. The analysis is based on parametrization of sentences complicated for articulation. Experimental dataset consists of 101 PD patients with different disease progress and 53 healthy controls. For the purpose of feature selection we employed mRMR (minimum Redundancy Maximum Relevance) method.

Keywords

Parkinson’s disease, hypokinetic dysarthria, speech parameterization, speech signal processing, objective analysis, diagnosis, monitoring, progress estimation

Released

28.04.2016

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních

Location

Brno

ISBN

978-80-214-5350-0

Book

Proceedings of the 22nd Conference STUDENT EEICT 2016

Edition number

první

Pages from

518

Pages to

522

Pages count

5

Documents

BibTex


@inproceedings{BUT124265,
  author="Tomáš {Kiska}",
  title="Acoustic Analysis of Sentences Complicated for Articulation in Patients with Parkinson's Disease",
  annote="This paper deals with acoustic analysis of hypokinetic dysarthria. Hypokinetic dysarthria is
a speech motor dysfunction that is present in approximately 90% of patients with Parkinson’s disease
(PD). The work is mainly focused on parameterization techniques that can be used to diagnose or
monitor this disease as well as estimate its progress. Acoustic analysis can be used to estimate a grade
of hypokinetic dysarthria in fields of phonation, articulation, prosody and speech fluency. Regarding
the parameterization, new features based on RASTA method were proposed. The analysis is based on
parametrization of sentences complicated for articulation. Experimental dataset consists of 101 PD
patients with different disease progress and 53 healthy controls. For the purpose of feature selection
we employed mRMR (minimum Redundancy Maximum Relevance) method.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních",
  booktitle="Proceedings of the 22nd Conference STUDENT EEICT 2016",
  chapter="124265",
  howpublished="print",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních",
  year="2016",
  month="april",
  pages="518--522",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních",
  type="conference paper"
}