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区分性别的汉语方言识别系统

GMM Based Gender Distinguishing and Chinese Dialect Recognition System
下载PDF
导出
摘要 提出一种基于GMM的区分不同性别的汉语方言识别系统,系统提取语音的RASTA-PLP特征,在方言电话语音库上进行仿真实验,结果表明在GMM模型阶数为32时,系统的识别率可达到98.66%。同时还将RASTA-PLP特征与SDC特征对比,结果表明系统识别率最高可提高6.05%,且RASTA-PLP特征在性别分类方面优于SDC。 A GMM based gender distinguishing and Chinese dialect recognition system are described.RASTA-PLP coefficients are adopted for model training.The system is tested on the dialect telephone speech corpus.Results show that the recognition rate can be as high as 98.66% when the number of components in GMM is 32.At the same time RASTA-PLP feature and shifted delta cepstrum（SDC） feature are compared.Results show that the increased performance can attain 6.05% at most,and RASTA-PLP feature is superior to SDC in gender classification.
作者 王侠 顾明亮 高原 马勇
机构地区 徐州师范大学物理与电子工程学院 徐州师范大学语言科学学院
出处 《电声技术》 2011年第12期39-41,46,共4页 Audio Engineering
关键词 方言识别 RASTA-PLP GMM SDC dialect recognition RASTA-PLP GMM SDC
分类号 TN912.3 [电子电信—通信与信息系统]
  • 相关文献

参考文献8

  • 1ZISSMAN M A.Comparison of four approaches to automatic language identification of telephone speech[J].IEEE Trans.Speech and Audio Proceeding,1996,4 (1):31-44.
  • 2顾明亮,夏玉果,张长水,杨亦鸣.基于AdaBoost的汉语方言辨识[J].东南大学学报（自然科学版）,2008,38(4):585-588. 被引量：3
  • 3HARB H,CHEN L.Voice-based gender identification in multimedia applications[J].International Journal of Pattern Recognition and Artificial Intellligence,2005,19 (2):63-78.
  • 4邓英,欧贵文.基于HMM的性别识别[J].计算机工程与应用,2004,40(15):74-75. 被引量：8
  • 5LI W,KIM D J,KIM C H,et al.Voiced-based recognition system for non-semantics information by language and gender[C] //Prcceeding of IEEE International Symposium on Electronic Commerce and Security.[S.1.] :IEEE Press,2010(1):84-88.
  • 6HERMANSKY H,MORGAN N,BAYYA A,et al.RASTA-PLP speech analysis technique[C] //Proceeding of IEEE International Conference on Acoustics,Speech,and Signal Processing.[S.1.] :IEEE Press,1992(1):121-124.
  • 7KOHLER M A,KENNEDY M.Language identification using shifted delta cepstra[C] //Proceeding of IEEE International Conference on Digital Signal Processing.[S.1.] :IEEE Press,2003 (1):3-69.
  • 8ZHANG W Q,HE L,DENG Y,et al.Time-frequency cepstral feature and heteroscedastic linear discriminant analysis for language recognition[J].IEEE Trans.Audio,Speech,and Language Processing,2011,19 (2):266-276.

二级参考文献19

  • 1顾明亮,沈兆勇.基于语音配列的汉语方言自动辨识[J].中文信息学报,2006,20(5):77-82. 被引量：19
  • 2Burton A M ,Bruce V,Dench N.What's the difference between men and women?Evidence from facial measurement.Perception, 1993; 22:153～176
  • 3Parris Eluned S,Carey Michael J. Language Independent Gender Identification. ICASSP 1996,1996 ;2: 685～688
  • 4P Olsen,S Dharanipragada. An Efficient Integrated Gender Detection Scheme and Time Mediated Averaging of Gender Dependent Acoustic Models.submitted to Eurospeech,2003
  • 5A D Gordon. Classification. New York:Chapman & Hall/CRC,1999
  • 6Stefan Slomka,Sridha Sridharan. AUTOMATIC GENDER IDENTIFICATION UNDER ADVERSE CONDITIONS.Session ThMD Speaker Recognition and Language Identification, 1997; 5: 2307～2310
  • 7Qin Jin,Tanja Schultz,Alex WaibeI.PHONETIC SPEAKER IDENTIFICATION.ICSLP-2002 TECHNICAL PROGRAM,2002
  • 8L Walawalkar,Mohammad Yeasin,Anand M Narasimhamurthy et al. Support Vector Learning for Gender Classification Using Audio Visual Cues: A Comparison. SVM 2002
  • 9http://htk.eng.cam.ac.uk
  • 10Muthusamy Y K, Bamard E, Cole R A, Reviewing automatic language identification [ J ]. IEEE Signal Processing Magazine, 1994,11 ( 4 ) -33 - 41.

共引文献9

电声技术
2011年 第12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