Title :
SVM-based speech endpoint detection using contextual speech features
Author :
Ramírez, J. ; Yélamos, P. ; Górriz, J.M. ; Segura, J.C.
Author_Institution :
Dept. of Signal Theor., Granada, Spain
fDate :
3/30/2006 12:00:00 AM
Abstract :
Shown is an effective speech endpoint detection algorithm using a trained support vector machine (SVM) and a feature vector including contextual information speech features. With this and other innovations the proposed algorithm yields high discrimination and reports significant improvements over standard methods and algorithms defining the decision rule in terms of averaged subband speech features.
Keywords :
speech recognition; support vector machines; contextual speech features; speech endpoint detection algorithm; subband speech feature; support vector machine;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20064068