DocumentCode :
3227488
Title :
A novel voice activity detection method using energy statistical complexity
Author :
Zhao, Huan ; Wang, Gangjin ; Peng, Xiujuan
Author_Institution :
Sch. of Comput. & Commun., Hunan Univ., Changsha, China
fYear :
2010
fDate :
23-26 Sept. 2010
Firstpage :
1175
Lastpage :
1179
Abstract :
In this paper, the nonlinear dynamic characteristics of the statistical complexity were applied to the voice activity detection (VAD). By combining it with the energy feature, we present a new VAD method that is energy statistics complexity (ESC) algorithm, using fuzzy c-Means clustering algorithm and Bayesian information criterion algorithm to estimate the thresholds of the ESC characteristic, and using dual threshold method for VAD. Experiments on the TIMIT continuous speech database show that at low SNR environments, ESC method is superior to the energy spectrum entropy (ESE) method. Especially in the vehicle noise and vehicle interior noise environments, ESC method shows better detection performance.
Keywords :
Bayes methods; fuzzy set theory; speech processing; Bayesian information criterion algorithm; ESC algorithm; ESE method; VAD; dual threshold method; energy feature; energy spectrum entropy; energy statistical complexity; fuzzy c-means clustering algorithm; nonlinear dynamic characteristic; vehicle interior noise environment; voice activity detection; Complexity theory; Entropy; Robustness; Signal to noise ratio; energy spectral entropy; energy statistical complexity; speech processing; statistical complexity; voice activity detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010 IEEE Fifth International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-6437-1
Type :
conf
DOI :
10.1109/BICTA.2010.5645091
Filename :
5645091
Link To Document :
بازگشت