基于改进Kohonen网络训练算法的说话人识别系统

Text-Independent Speaker Recognition Based on Improved Kohonen Training Algorithm

下载PDF

导出

摘要与文本无关的说话人识别方法是当前说话人识别技术的研究重点.本文将自组织特征映射(SOFM)网络用于矢量量化中码书的形成,改进了训练算法,并基于改进算法进行了与文本无关的说话人识别.经实验结果证明,本文的方法改善了码本的性能,提高了说话人识别的识别率.

作者张庆芳赵鹤鸣苏秦

机构地区苏州大学电子信息学院

出处《信号处理》 CSCD 北大核心 2005年第z1期200-203,共4页 Journal of Signal Processing

基金本文受国家自然科学基金资助(项目编号60172016)

关键词说话人识别与文本无关自组织特征映射(SOFM)

参考文献7

1[1]F. Soong, A. Rosenberg, L. Rabiner, B.-H. Juang. A vector quan-tization approach to speaker recognition[J]. Proc. of the InternationalConference on Acoustics, Speech,and Signal Processing (ICASSP). 1985,1:387-390.
2[2]Linde Y,Buzo A, Gray R.M. An algorithm for vector quantizer design[J]. IEEE Transactions on Communication.1980,28:84-95.
3[3]H.C.Huang,J.S.Pan,Z.M.Lu,et.al. Vector Quantization Based on Genetic Simulated Annealing [J]. Signal Processing.2001.81(7):1513-1523.
4[4]Chen Ke,Wu Ting-Yao,Zhang Hong-Jiang. On the use of nearest feature line for speaker identification [J]. Pattern Recognition Letters.2002,23(4): 1735-1746.
5[5]K S Wu,J C Lin. Fast VQ encoding by an efficient kick-out condition[J].IEEE Transactions on Circuits and Systems for Video Technology,2000,10(1):59- 62.
6[6]Kohonen. Self-Organization and Associative Memory[M].3rd ed. SPringer-Verlag. 1989.
7陆哲明,孙圣和.基于自组织特征映射神经网络的矢量量化[J].中国图象图形学报（A辑）,2000,5(10):846-850. 被引量：10

11，Linde Y,Buzo A，Gray R M.An algorithm for vector quantizer design.IEEE Trans.On Commun.,1980,28(1):84～95.
22，Gersho A,Gray R M.Vector quantization and signalcompression.Boston,MA:Kluwer,1992.
33，Nasrabadi N M,Feng Y.Vector quantization of images based upon the Kohonen self-organizing feature maps.Proc.ICNN,San Diego,1988,1:101～108.
44，Bei C D,Gray R M.An improvement on minimum distortion encoding algorithm for vector quantization.IEEE Trans.On Commun.,1985,33(10):1132～1133.

信号处理

2005年第z1期

内容加载中请稍等...