Using redundant parallel architecture to improve speaker recognition performance  

作　　者：Zhengquan QIU Junxun YIN Caiyun FAN 

机构地区：[1]School Electronic and Information Engineering, South China University of Technolog, Guangzhou Guangdong 510640, China [2]School of Mathematical Sciences, South China University of Technology, Guangzhou Guangdong 510640, China

出　　处：《控制理论与应用（英文版）》2008年第2期221-223,共3页

基　　金：the National Natural Science Foundation of China (No. 60171043, 60371046)

摘　　要：In this paper, we propose two kinds of modifications in speaker recognition. First, the correlations between frequency channels are of prime importance for speaker recognition. Some of these correlations are lost when the frequency domain is divided into sub-bands. Consequently we propose a particularly redundant parallel architecture for which most of the correlations are kept. Second, generally a log transformation used to modify the power spectrum is done after the filter-bank in the classical spectrum calculation. We will see that performing this transformation before the filter bank is more interesting in our case. In the processing of recognition, the Gaussian mixture model （GMM） recognition arithmetic is adopted. Experiments on speech corrupted by noise show a better adaptability of this approach in noisy environments, comoared with a conventional device, esoeciallv when oruning of some recognizers is performed.In this paper, we propose two kinds of modifications in speaker recognition. First, the correlations between frequency channels are of prime importance for speaker recognition. Some of these correlations are lost when the frequency domain is divided into sub-bands. Consequently we propose a particularly redundant parallel architecture for which most of the correlations are kept. Second, generally a log transformation used to modify the power spectrum is done after the filter-bank in the classical spectrum calculation. We will see that performing this transformation before the filter bank is more interesting in our case. In the processing of recognition, the Gaussian mixture model （GMM） recognition arithmetic is adopted. Experiments on speech corrupted by noise show a better adaptability of this approach in noisy environments, comoared with a conventional device, esoeciallv when oruning of some recognizers is performed.

关 键 词：CORRELATIONS Redundant parallel architecture Log transformation GMM 

分 类 号：TN912.34[电子电信—通信与信息系统]