Paper Info
Title
Improving the intelligibility of dysarthric speech
Abstract
Dysarthria is a speech motor disorder usually resulting in a substantive decrease in speech intelligibility by the general population. In this study, we have significantly improved the intelligibility of dysarthric vowels of one speaker from 48% to 54%, as evaluated by a vowel identification task using 64 CVC stimuli judged by 24 listeners. Improvement was obtained by transforming the vowels of a speaker with dysarthria to more closely match the vowel space of a non-dysarthric (target) speaker. The optimal mapping feature set, from a list of 21 candidate feature sets, proved to be one utilizing vowel duration and F1-F3 stable points, which were calculated using shape-constrained isotonic regression. The choice of speaker-specific or speaker-independent vowel formant targets appeared to be insignificant. Comparisons with ''oracle'' conditions were performed in order to evaluate the analysis/re-synthesis system independently of the transformation function.
Year
DOI
Venue
2007
10.1016/j.specom.2007.05.001
Speech Communication
Keywords
Field
DocType
dysarthria,speech transformation,dysarthric vowel,speaker-independent vowel formant target,speech modification,speech motor disorder,speech intelligibility,intelligibility,cvc stimulus,candidate feature set,optimal mapping feature set,vowel space,dysarthric speech,utilizing vowel duration,speech processing,vowel identification task,isotonic regression
Speech processing,Population,Transformation (function),Computer science,Motor disorder,Speech recognition,Vowel,Formant,Dysarthria,Intelligibility (communication)
Journal
Volume
Issue
ISSN
49
9
Speech Communication
Citations 
PageRank 
References 
26
2.06
5
Authors
6
Name
Order
Citations
PageRank
Alexander B. Kain1515.90
John-Paul Hosom223123.43
Xiaochuan Niu3506.72
Jan P. H. van Santen451499.66
M Fried-Oken5658.39
Janice Staehely6403.64