Assessing Dysarthria severity using global statistics and boosting
Publication
, Conference
DeMino, A; Kubichek, R; Caves, K
Published in: Conference Record - Asilomar Conference on Signals, Systems and Computers
December 1, 2011
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.
Published In
Conference Record - Asilomar Conference on Signals, Systems and Computers
DOI
ISSN
1058-6393
ISBN
9781467303231
Publication Date
December 1, 2011
Start / End Page
1103 / 1106
Citation
APA
Chicago
ICMJE
MLA
NLM
DeMino, A., Kubichek, R., & Caves, K. (2011). Assessing Dysarthria severity using global statistics and boosting. In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 1103–1106). https://doi.org/10.1109/ACSSC.2011.6190184
DeMino, A., R. Kubichek, and K. Caves. “Assessing Dysarthria severity using global statistics and boosting.” In Conference Record - Asilomar Conference on Signals, Systems and Computers, 1103–6, 2011. https://doi.org/10.1109/ACSSC.2011.6190184.
DeMino A, Kubichek R, Caves K. Assessing Dysarthria severity using global statistics and boosting. In: Conference Record - Asilomar Conference on Signals, Systems and Computers. 2011. p. 1103–6.
DeMino, A., et al. “Assessing Dysarthria severity using global statistics and boosting.” Conference Record - Asilomar Conference on Signals, Systems and Computers, 2011, pp. 1103–06. Scopus, doi:10.1109/ACSSC.2011.6190184.
DeMino A, Kubichek R, Caves K. Assessing Dysarthria severity using global statistics and boosting. Conference Record - Asilomar Conference on Signals, Systems and Computers. 2011. p. 1103–1106.
Published In
Conference Record - Asilomar Conference on Signals, Systems and Computers
DOI
ISSN
1058-6393
ISBN
9781467303231
Publication Date
December 1, 2011
Start / End Page
1103 / 1106