Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Strategic Study of CAE >> 2010, Volume 12, Issue 2

A new score normalizaion algorithm based on EMD-Tnorm for speaker verification

1. College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;

2. School of Computer Science,Nanjing University of Science & Technology, Nanjing 210094, China;

3. School of Mathematics & Information Engineering , Jiaxing University, Jiaxing, Zhejiang 314001, China

Funding project:浙江省自然科学基金资助项目(Y1090649);浙江省教育厅科研资助项目(Y200805349) Received: 2008-04-18 Available online: 2010-02-03 10:02:22.000

Next Previous

Abstract

In this paper, the verification system from two aspects was improved. On one hand, we extended MixMax model that the EMD (earth mover's distance) can be applied, which can remove the disturbance of noise; on the other hand, we improved the Tnorm score normalization method based on the EMD. Experimental results show that this method can compensate the speaker-dependent and test-dependent variability, also show a stable performance improvement by decreasing the FA and FR.

Figures

图1

图2

图3

图4

References

[ 1 ] Dijana P D, Asmaa E H, Gerard Chollet.Text -independent speaker verification state of the art and challenges [ J] .LNCS, 2007 , 135 -169 link1

[ 2 ] Sturim D E, Reynolds D A.Speaker adaptive cohort selective for Tnorm in text -independent speaker verification [ J] .ICASSP, 2005 , 1 : 741 -744 link1

[ 3 ] Daniel R C, Julian F A, Joaquin G R.Speaker verification using speaker -and test -dependent fast score normalization [ J] .Pat- tern Recognition Letters, 2007 , 28 : 90 -98 link1

[ 4 ] Auckenthaler R, Carey M,Lloyd -Tomas H.Score normalization for text -independent speaker verification systems [ J ] .Digital Signal Process, 2000 , 10 :42 -54 link1

[ 5 ] Reynolds D A, Quatieri T F.Speaker verification using adapted Gaussian Mixture Models [ J] .Digital Signal Process, 2000 , 10 : 19 -41 link1

[ 6 ] Thilo Stadelmann, Bernd Freisleben.Fast and robust speaker clustering using the earth mover’ s distance and mixmax models [ J] .ICASSP, 2006 , 1 : 989 -992 link1

[ 7 ] Rubner Y, Tomasi C, Guibas L J.The earth mover’ s distance as a metric for image retrieval [ J] .International Journal of Comput- er Vision, 2000 ,40 : 99 -121 link1

[ 8 ] 郑榕,张树武,徐波.基于特征规整和评分规整的说话人确认研究[J].中文信息学报,2006,20(6):75-82 link1

[ 9 ] 刘明辉,陈继旭,李辉,等.基于TZNormalization规整的话者确认阈值选取[J].数据采集与处理,2005,20(3):311-317 link1

Related Research