Voice activity detection based on the bispectrum - Details

Author：

Dou, Hui-Jing (Dou, Hui-Jing.) | Wu, Zhao-Yang (Wu, Zhao-Yang.) | Feng, Yan (Feng, Yan.) | Qian, Yan-Zhou (Qian, Yan-Zhou.)

Indexed by：

EI Scopus

Abstract：

In　order　to　improve　the　performance　of　voice　activity　detection　under　multiple　noise　environments,　a　new　voice　activity　detection　algorithm　based　on　the　bispectrum　was　presented.　This　method　detect　the　speech　signal　by　using　the　special　slice　of　the　bispectrum.　The　performance　of　the　algorithm　was　compared　with　the　voice　activity　detection　algorithm　in　standard　G.729　annex　B　of　ITU　in　experimental　simulation.　Experimental　results　show　that　the　algorithm　has　high　classification　accuracy　and　stability.　©　2010　IEEE.

Keyword：

Signal detection Speech recognition

Author Community：

[ 1 ] [Dou, Hui-Jing]School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 2 ] [Wu, Zhao-Yang]School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 3 ] [Feng, Yan]School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 4 ] [Qian, Yan-Zhou]School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China