Publication detail

An Automatic Diagnosis and Assessment of Dysarthric Speech using Speech Disorder Specific Prosodic Features

VYAS, G. DUTTA, M. PŘINOSIL, J. HARÁR, P.

Original Title

An Automatic Diagnosis and Assessment of Dysarthric Speech using Speech Disorder Specific Prosodic Features

English Title

An Automatic Diagnosis and Assessment of Dysarthric Speech using Speech Disorder Specific Prosodic Features

Type

conference paper

Language

en

Original Abstract

To diagnose and classify the dysarthria speech, speech language pathologist (SLP) conduct a listening test. On the basis of the scores given by listeners the dysarthria is diagnosed and assessed. The above mentioned method is costly, time consuming and not very accurate. Unlike the traditional method, this research proposes an automatic diagnosis and assessment of dysarthria. The aim of this paper is to diagnose and classify the severity of dysarthria. The speech disorder specific prosodic features are selected by using genetic algorithm. The diagnosis and assessment of dysarthria speech is done by support vector machines. During diagnosis the classification accuracy of 98% has been achieved. And 87% of the dysarthria speech utterances are correctly classified. The standard UASPEECH database has been used in this work.

English abstract

To diagnose and classify the dysarthria speech, speech language pathologist (SLP) conduct a listening test. On the basis of the scores given by listeners the dysarthria is diagnosed and assessed. The above mentioned method is costly, time consuming and not very accurate. Unlike the traditional method, this research proposes an automatic diagnosis and assessment of dysarthria. The aim of this paper is to diagnose and classify the severity of dysarthria. The speech disorder specific prosodic features are selected by using genetic algorithm. The diagnosis and assessment of dysarthria speech is done by support vector machines. During diagnosis the classification accuracy of 98% has been achieved. And 87% of the dysarthria speech utterances are correctly classified. The standard UASPEECH database has been used in this work.

Keywords

Dysarthria speech; diagnosis; assessment; speech disorder; prosodic features; support vector machines

Released

27.06.2016

Location

Vieanna, Austria

ISBN

978-1-5090-1287-9

Book

2016 39th International Conference on Telecommunications and Signal Processing (TSP)

Pages from

515

Pages to

519

Pages count

4

BibTex


@inproceedings{BUT127569,
  author="Garima {Vyas} and Malay Kishore {Dutta} and Jiří {Přinosil} and Pavol {Harár}",
  title="An Automatic Diagnosis and Assessment of Dysarthric Speech using Speech Disorder Specific Prosodic Features",
  annote="To diagnose and classify the dysarthria speech, speech language pathologist (SLP) conduct a listening test. On the basis of the scores given by listeners the dysarthria is diagnosed and assessed. The above mentioned method is costly, time consuming and not very accurate. Unlike the traditional method, this research proposes an automatic diagnosis and assessment of dysarthria. The aim of this paper is to diagnose and classify the severity of dysarthria. The speech disorder specific prosodic features are selected by using genetic algorithm. The diagnosis and assessment of dysarthria speech is done by support vector machines. During diagnosis the classification accuracy of 98% has been achieved. And 87% of the dysarthria speech utterances are correctly classified. The standard UASPEECH database has been used in this work.",
  booktitle="2016 39th International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="127569",
  howpublished="online",
  year="2016",
  month="june",
  pages="515--519",
  type="conference paper"
}