Assessing Dysarthria severity using global statistics and boosting


Conference Paper

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. © 2011 IEEE.

Full Text

Duke Authors

Cited Authors

  • DeMino, A; Kubichek, R; Caves, K

Published Date

  • December 1, 2011

Published In

Start / End Page

  • 1103 - 1106

International Standard Serial Number (ISSN)

  • 1058-6393

International Standard Book Number 13 (ISBN-13)

  • 9781467303231

Digital Object Identifier (DOI)

  • 10.1109/ACSSC.2011.6190184

Citation Source

  • Scopus