Discriminative Decision Function Based Scoring Method Used in Soeaker Verification  

作　　者：LIANG Chunyan ZHANG Xiang YAN Yonghong 

机构地区：[1]The Key Laboratory of Speech Acoustics and Content Understanding,Institute of Acoustics,Chinese Academy of Sciences,Beijing 100190,China

出　　处：《Chinese Journal of Electronics》2012年第4期692-696,共5页电子学报（英文版）

基　　金：This work is supported by the National Natural Science Foundation of China （No.10925419, No.90920302, No.61072124, No.11074275, No.11161140319） and the Strategic Priority Research Program of the Chinese Academy of Sciences （No.XDA06030100）.

摘　　要：Decision function of log likelihood ratio derived from classical hypothesis testing theory is widely used in Gaussian mixture model based speaker recognition system. This paper introduces a discriminative decision function based scoring method for speaker recognition with the state-of-the-art Joint factor analysis （JFA） system. In the scoring module of JFA system, an approximate form of the decision function is proposed. Based on the approximation, we present a discriminative decision function by re-estimating the contribution of each speech sound unit to the decision function to further improve the performance of speaker verification. The discriminative decision function is used to exploit the individual Gaussian component for better classification. The experiments are carried on the core conditions of National institute of standards and technology （NIST） 2010 speaker recognition evaluation data. The experimental results show that the proposed scoring method outperforms the conventional frame-by-frame strategy on the whole.

关 键 词：Speaker verification Joint factor analysis （JFA） Discriminative decision function. 

分 类 号：TN912.34[电子电信—通信与信息系统] TU753[电子电信—信息与通信工程]