Support Vector Machine based Voice Activity Detection

2006 ◽  
Author(s):  
M. Baig ◽  
S. Masud ◽  
M. Awais
Keyword(s):  
Support Vector Machine ◽  
Voice Activity Detection ◽  
Support Vector ◽  
Activity Detection ◽  
Voice Activity

scholarly journals Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine

Entropy ◽  
2016 ◽  
Vol 18 (8) ◽  
pp. 298 ◽  
Author(s):  
R. Johny Elton ◽  
P. Vasuki ◽  
J. Mohanalin
Keyword(s):  
Support Vector Machine ◽  
Voice Activity Detection ◽  
Fuzzy Entropy ◽  
Support Vector ◽  
Activity Detection ◽  
Voice Activity

Improved voice activity detection algorithm using wavelet and support vector machine

2010 ◽  
Vol 24 (3) ◽  
pp. 531-543 ◽  
Author(s):  
Shi-Huang Chen ◽  
Rodrigo Capobianco Guido ◽  
Trieu-Kien Truong ◽  
Yaotsu Chang
Keyword(s):  
Support Vector Machine ◽  
Detection Algorithm ◽  
Voice Activity Detection ◽  
Support Vector ◽  
Activity Detection ◽  
Voice Activity

scholarly journals Voice activity detection using smoothed-fuzzy entropy (smFuzzyEn) and support vector machine

2019 ◽  
Vol 17 (1) ◽  
Author(s):  
R. Johny Elton ◽  
P. Vasuki ◽  
J. Mohanalin ◽  
J. S. Gnanasekaran
Keyword(s):  
Support Vector Machine ◽  
Signal To Noise Ratio ◽  
Voice Activity Detection ◽  
Fuzzy Entropy ◽  
Support Vector ◽  
Svm Classifier ◽  
Activity Detection ◽  
Noisy Speech ◽  
Feature Vectors ◽  
Voice Activity

In this paper a novel voice activity detection approach using smoothed fuzzy entropy (smFuzzyEn) feature using support vector machine is proposed. The proposed approach (smFESVM) uses total variation filter and Savitzky-Golay filter to smooth the FuzzyEn feature extracted from the noisy speech signals. Also, convolution of the first order difference of TV filter and noisy fuzzy entropy feature (conFETV') is also proposed. The obtained smoothed feature vectors are further normalized using min-max normalization and the normalized feature vectors train SVM model for speech/non-speech classification. The proposed smFESVM method shows better discrimination of noise and noisy speech when tested under various nonstationary background noises of different signal-to-noise ratio levels. 10 – fold cross validation was used to validate the efficacy of the SVM classifier. The performance of the smFESVM is compared against various algorithms and comparison suggests that the results obtained by the smFESVM is efficient in detecting speech under low SNR conditions with an accuracy of 93.88%.

Sign in / Sign up

Export Citation Format

Share Document