Title :
A novel two-step SVM classifier for voiced/unvoiced/silence classification of speech
Author :
Qi, Fengyan ; Bao, Changchun ; Liu, Yan
Author_Institution :
Speech & Audio Signal Process. Lab, Beijing Univ. of Technol., China
Abstract :
In this paper, a novel method for voiced/unvoiced/silence of speech classification using the support vector machine (SVM) is proposed. This classifier can correctly classify speech frames into voiced frame, unvoiced frame and silence frame. The comparison of experimental results show that the proposed method outperforms other traditional methods. The performance of SVM for different kernel functions in the experiment was analyzed and discussed as well.
Keywords :
signal classification; speech processing; speech recognition; support vector machines; kernel functions; silence frame; speech classification; speech frames; support vector machine; two-step SVM classifier; unvoiced frame; voiced frame; Classification algorithms; Kernel; Machine learning algorithms; Neural networks; Pattern classification; Speech processing; Speech recognition; Statistical distributions; Support vector machine classification; Support vector machines;
Conference_Titel :
Chinese Spoken Language Processing, 2004 International Symposium on
Print_ISBN :
0-7803-8678-7
DOI :
10.1109/CHINSL.2004.1409590