DocumentCode :
2731392
Title :
A New Robust Voice Activity Detection method based on Genetic Algorithm
Author :
Farsinejad, M. ; Analoui, M.
Author_Institution :
Dept. of Comput. Eng., Iran Univ. of Sci. & Technol., Tehran
fYear :
2008
fDate :
7-10 Dec. 2008
Firstpage :
80
Lastpage :
84
Abstract :
In this paper we introduce an efficient genetic algorithm based voice activity detection (GA-VAD) algorithm. The inputs for GA-VAD are zero-crossing difference and a new feature that is extracted from signal envelope parameter, called MULSE (multiplication of upper and lower signal envelope). The voice activity decision is obtained using a Threshold algorithm with additional decision smoothing. The key advantage of this method is its simple implementation and its low computational complexity and introducing a new simple and efficient feature, MULSE, for solving the VAD problem. The MULSE parameter could be appropriate substitution for energy parameter in VAD problems. The GA-based VAD algorithm (GA-VAD) is evaluated using the Timit database. It is shown that the GA-VAD achieves better performance than G. 729 Annex B at any noise level with a high artificial-to-intelligence ratio.
Keywords :
genetic algorithms; speech recognition; genetic algorithm; high artificial-to-intelligence ratio; multiplication of upper and lower signal envelope; noise level; robust voice activity detection method; zero-crossing difference; Artificial intelligence; Computational complexity; Feature extraction; Genetic algorithms; Genetic engineering; Noise level; Robustness; Smoothing methods; Spatial databases; Speech coding; GA-VAD; Voice activity detection; genetic algorithm based VAD;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Telecommunication Networks and Applications Conference, 2008. ATNAC 2008. Australasian
Conference_Location :
Adelaide, SA
Print_ISBN :
978-1-4244-2602-7
Electronic_ISBN :
978-1-4244-2603-4
Type :
conf
DOI :
10.1109/ATNAC.2008.4783300
Filename :
4783300
Link To Document :
بازگشت