IMPROVING VOICE ACTIVITY DETECTION VIA WEIGHTING LIKELIHOOD AND DIMENSION REDUCTION  

作　　者：Wang Huanliang Han Jiqing Li Haifeng Zheng Tieran 

机构地区：[1]Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China

出　　处：《Journal of Electronics(China)》2008年第3期330-336,共7页电子科学学刊（英文版）

基　　金：Supported by the National Basic Research Program of China (973 Program) (No.2007CB311104)

摘　　要：The performance of the traditional Voice Activity Detection （VAD） algorithms declines sharply in lower Signal-to-Noise Ratio （SNR） environments. In this paper, a feature weighting likelihood method is proposed for noise-robust VAD. The contribution of dynamic features to likelihood score can be increased via the method, which improves consequently the noise robustness of VAD. Divergence based dimension reduction method is proposed for saving computation, which reduces these feature dimensions with smaller divergence value at the cost of degrading the performance a little. Experimental results on Aurora Ⅱ database show that the detection performance in noise environments can remarkably be improved by the proposed method when the model trained in clean data is used to detect speech endpoints. Using weighting likelihood on the dimension-reduced features obtains comparable, even better, performance compared to original full-dimensional feature.The performance of the traditional Voice Activity Detection (VAD) algorithms declines sharply in lower Signal-to-Noise Ratio (SNR) environments. In this paper, a feature weighting likeli- hood method is proposed for noise-robust VAD. The contribution of dynamic features to likelihood score can be increased via the method, which improves consequently the noise robustness of VAD. Divergence based dimension reduction method is proposed for saving computation, which reduces these feature dimensions with smaller divergence value at the cost of degrading the performance a little. Experimental results on Aurora II database show that the detection performance in noise environments can remarkably be improved by the proposed method when the model trained in clean data is used to detect speech endpoints. Using weighting likelihood on the dimension-reduced features obtains com- parable, even better, performance compared to original full-dimensional feature.

关 键 词：Voice Activity Detection （VAD） Weighting likelihood DIVERGENCE Dimension reduction Noise robustness 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]