The Voice Activity Detection Algorithm Based on Spectral Entropy and High-Order Statistics


Article Preview

The voice activity detection is one of the key technologies of variable rate speech coding. The development of speech coding technology requires higher performance of the detection. Based on the analysis of spectral entropy and high-order statistics of the basic definition and property of the foundation, this article proposes a voice activity detection algorithm which combines spectral entropy with high-order statistics. The algorithm can effectively detect the speech and non-speech segments, and can get reasonable results in a complex background noise environment.



Edited by:

Li Qiang




Q. Li et al., "The Voice Activity Detection Algorithm Based on Spectral Entropy and High-Order Statistics", Applied Mechanics and Materials, Vol. 624, pp. 495-499, 2014

Online since:

August 2014




* - Corresponding Author

[1] Zhang Xiong, Chen Liang, Yang Jibin modern voice processing technology and application[M]. Beijing: Mechanical Industry Press, 2003, pp.268-273.

[2] Zhang Cui. Study on speech endpoint detection algorithm based on spectral entropy [D]. Hebei: Hebei University, 2010: 1-28.

[3] Wang let be, Chai peiqi. An improved speech endpoint detection method based on spectral entropy [J]. Information and Control, 2004, 33 (1), pp.77-81.

[4] Li K, Swamy M N S, Ahmad M O. An improved voice activity detection using higher order statistics [J]. Speech and Audio Processing, IEEE Transactions on, 2005, 13(5), pp.965-974.


[5] Lei J, Wang J, Yang Z. Robust Voice Activity Detection Based on Spectral Entropy and Two-Stage Mel-Warped Wiener Filtering[C]/Intelligent Information Technology Application, 2008. IITA'08. Second International Symposium on. Shanghai, China. IEEE, 2008(2), pp.306-309.


[6] Yang X, Tan B, Ding J, et al. Comparative study on voice activity detection algorithm[C]/Electrical and Control Engineering (ICECE), 2010 International Conference on. Wuhan, China. IEEE, 2010, pp.599-602.


[7] Hao Z, Deming L. Research of Voice Activity Detection Algorithm[C]/Proceedings of the 2011 International Conference on Computational and Information Sciences. Chengdu, Sichuan, China. IEEE Computer Society, 2011, pp.853-855.