期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于GMM的说话人识别系统设计与实现 被引量：2

Design and Implementation of Speaker Identification System Based on GMM
下载PDF
导出
摘要 现代通信中,说话人的身份认证技术一直是通信行业研究的重点和热点。而基于GMM和MFCC的说话人识别技术,是目前为止相对成熟和常用的方法。对说话人识别系统的构成做了相关的研究,并通过MATLAB编程,设计了一款以MFCC作为特征参数,基于GMM模型的说话人识别系统。经过实验测试,本系统能基本满足工作及家庭生活环境下的说话人识别需要。 In modern communication,the technology of the speaker's ID authentication is the focus of research and hotspots in communications industry.At present,the speaker identification technology, based on GMM and MFCC,is usable and poplar.In this paper,the composition of speaker identification system is researched and a system which uses Mel frequency cepstral coefficients (MFCC )as feature parameter and GMM for speaker model is designed by Matlab.The test results show that the system can generally meet the requirements of identification for work and life.
作者 刘冰 滕广超 林嘉宇
机构地区 国防科学技术大学电子科学与工程学院 武警湖南省总队湘潭市支队 武警黄金一总队通信科
出处 《微处理机》 2014年第3期63-65,共3页 Microprocessors
关键词 说话人识别 MEL倒谱系数 混合高斯模型 Speaker Recognition MFCC GMM
分类号 TN912.34 [电子电信—通信与信息系统]
  • 相关文献

参考文献3

二级参考文献30

  • 1陈伟兵,周凌宏,肖中举.耳蜗基底膜振动模型的建立与应用[J].中国医学物理学杂志,2007,24(3):221-223. 被引量：10
  • 2Boll S F. Suppression of acoustic noise in speech using spectral subtraction [J]. IEEE Trans on ASSP, 1979, 27: 113 - 120.
  • 3Lockwood P, Boudy J. Experiments with a nonlinear spectral subtractor (NSS), hidden Markov models and the projection of robust speech recognition in ears [J]. Speech Communication, 1992, 11(6) : 215 - 228.
  • 4Moon S Y, Hwang J N. Noisy speech recognition via wavelet coefficient enhancement [C]// Proc OEEE 26th Asilomar Conf Signals, Syst, Comput. Monterey, CA, 1992:1086 - 1090.
  • 5Pelecanos J, Sridharan S. Feature warping for robust speaker verification [C]//Proc Odyssey. Crete, Greece, 2001: 213- 218.
  • 6Bing X, Upendra V C. Short-time Gaussianization for robust speaker verification [C]// Proc ICASSP. Orlando, USA, 2002 (1): 681-684.
  • 7Hermansky H, Morgan N. RASTA processing of speech [J]. IEEE Trans on Speech and Audio Processing, 1994, 2(4) : 578 - 589.
  • 8Reynolds D A. Channel robust speaker verification via feature mapping [C]// Proc 1CASSP. Hongkong, China, 2003 (2) : 53 - 56.
  • 9邓菁.电话信道下多说话人识别研究[D].北京:清华大学,2007.
  • 10Vogt R, Sridharan S. Experiments in session variability modeling for speaker verification [C]// Proc ICASSP. Toulouse, France. 2006:897-900.

共引文献9

同被引文献31

  • 1刘敬伟,徐美芝,郑忠国,程乾生.基于DTW的语音识别和说话人识别的特征选择[J].模式识别与人工智能,2005,18(1):50-54. 被引量：13
  • 2于明,袁玉倩,董浩,王哲.一种基于MFCC和LPCC的文本相关说话人识别方法[J].计算机应用,2006,26(4):883-885. 被引量：14
  • 3Reynolds D A, Quatier T F, Dram R B. Speaker verifica- tion using adapted Gaussian mixture models [ J ]. Digital Singal Processing , 2000,10 : 19-24.
  • 4Reynolds D A, Campbell W, Gleason T T. The 2004 MIT Lincoln laboratory speaker recognition system [ A ]. In Pro- cessdings of ICASSP. Philadel Pbia. USA: [ s. n. ] ,2008.
  • 5Reynolds D A, Rose R. Robust text-independent speaker i- dentification using Gaussian mixture speaker models [ J ]. IEEE Trans on Speech and Audio Processing, 1995, 3 ( 1 ) : 72-83.
  • 6Frey B, Dueck D. Clustering by passing messages between data points[J]. Science, 2007, 315(5184) :972-976.
  • 7Zhong Y C, Hua X. Study on speech control of turning movements of the multifunctional nursing bed [ J ]. Ad- vances in Intelligent and Soft Computing, 2012 ( 1 ) : 67- 72.
  • 8Agrawal U K, Chandra M, Badgaiyan C. Fractional fou- rier transform combination with MFCC based speaker iden- tification in clean environment[ J]. International Journal of Advanced Science, Engineering and Technology, 2012, 1 ( 1 ) :26-28.
  • 9Yuan Y J, Zhao P H, Zhou Q. Research of speaker rec- ognition based on combination of LPCC and MFCC [ C ]// Proc of IEEE International Conference on IntelLigent Com- puting and Intelligent Systems. [ S. 1. ] : IEEE Press, 2010 : 765-767.
  • 10蒋晔,唐振民.GMM文本无关的说话人识别系统研究[J].计算机工程与应用,2010,46(11):179-182. 被引量：27

引证文献2

二级引证文献2

微处理机
2014年 第3期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部