Deakin University
Browse

File(s) under permanent embargo

Quantitative assessment of syllabic timing deficits in ataxic dysarthria

conference contribution
posted on 2018-01-01, 00:00 authored by Bipasha KashyapBipasha Kashyap, Pubudu PathiranaPubudu Pathirana, Malcolm Horne, Laura Power, David Szmulewicz
Parametric analysis of Cerebellar Dysarthria (CD)
may be valuable and more informative compared to its clinical
assessment. A quantifiable estimation of the timing deficits in
repeated syllabic utterance is described in the current study.
Thirty-five individuals were diagnosed with cerebellar ataxia to
varying degrees and twenty-six age-matched healthy controls
were recruited. To automatically detect the local maxima of each
syllable in the recorded speech files, a topographic prominence
incorporated concept is designed. Subsequently, four acoustic
features and eight corresponding parametric measurements are
extracted to identify articulatory deficits in ataxic dysarthria.
A comparative study on the behaviour of these measures for
dysarthric and non-dysarthric subjects is presented in this
paper. The results are further explored using a dimension-reduction
tool (Principal Component Analysis) to emphasize
variation and bring out the strongest discriminating patterns in
our feature dataset.

History

Event

IEEE Engineering in Medicine and Biology Society. Conference (40th : 2018 : Honolulu, Hawaii)

Series

IEEE Engineering in Medicine and Biology Society Conference

Pagination

425 - 428

Publisher

Institute of Electrical and Electronics Engineers

Location

Honolulu, Hawaii

Place of publication

Piscataway, N.J.

Start date

2018-07-18

End date

2018-07-21

ISSN

1557-170X

eISSN

1558-4615

ISBN-13

9781538636466

Language

eng

Publication classification

E Conference publication; E1 Full written paper - refereed

Copyright notice

2018, IEEE

Editor/Contributor(s)

[Unknown]

Title of proceedings

EMBC 2018 : Proceedings of the 40th IEEE Engineering in Medicine and Biology Society Annual International Conference