DocumentCode
1931391
Title
Assessing Dysarthria severity using global statistics and boosting
Author
DeMino, A. ; Kubichek, R. ; Caves, Kevin
fYear
2011
fDate
6-9 Nov. 2011
Firstpage
1103
Lastpage
1106
Abstract
A new method for automatic assessment of Dysarthria severity is described. It uses the forward selection method (FSM) on global statistics of low-complexity features to find effective feature sets. FSM is embedded in a boosting algorithm that combines multiple weak classifiers to achieve a single strong classifier. Unlike standard boosting, this uses nonlinear class boundaries and unique feature sets per iteration. Results on a 39 speaker dysarthria database are described.
Keywords
iterative methods; medical disorders; pattern classification; speech processing; statistical analysis; Dysarthria severity automatic assessment; FSM; boosting algorithm; forward selection method; low-complexity features; multiple weak classifiers; nonlinear class boundaries; speaker dysarthria database; Boosting; Classification algorithms; Frequency measurement; Speech; Speech processing; Training; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Signals, Systems and Computers (ASILOMAR), 2011 Conference Record of the Forty Fifth Asilomar Conference on
Conference_Location
Pacific Grove, CA
ISSN
1058-6393
Print_ISBN
978-1-4673-0321-7
Type
conf
DOI
10.1109/ACSSC.2011.6190184
Filename
6190184
Link To Document