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

基于帧变换的与文本无关语种辨识系统的实现 被引量：1

Realization of a Text-Independent Speaker Recognition System Using Frame Transformation
下载PDF
导出
摘要 从基于GMM的与文本无关语种辨识系统的帧似然概率的统计特性出发,提出了针对语种辨识的GMM模型训练的新方法以及一种对目标和非目标模型帧似然概率进行补偿变换的方法。理论分析和实验结果表明,与GMM常用的最大似然穴ML雪变换相比,该变换能使系统提高辨识率达2.0%,因此,证明了该变换能够改善基于GMM的语种辨识系统的识别率。 This paper presents a compensation transformation method for the frame likelihood probability of objected and non-objected models. It is according to the statistical characteristic of the frame likelihood probability in the text-independent speaker recognition system based on GMM. The theory analysis and result of experiment indicates that the transformation can reduce the error recognition ratio to 2.0% ,comparing to Maximum Likelihood(ML) transformation which is mostly used in GMM.
作者 成新民
机构地区 湖州师范学院信息工程学院
出处 《微电子学与计算机》 CSCD 北大核心 2004年第12期131-134,共4页 Microelectronics & Computer
关键词 语种辨识 混合高斯模型 帧似然概率 Language identification, Gaussian mixture model, Frame likelihoods probability
分类号 TP391.42 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献6

  • 1Grieco J J, Pomales E O. Short Segment Automatic Language Identification Using Multifeature-transitionMatrix Approach Circuits and Systems. ISCAS'03. Proceedings of the2003International Symposium on, May 2003, 3: 25～28. Ⅲ-730-Ⅲ-733.
  • 2Wong E, Sridharan S. Comparison of Linear Prediction Cepstrum Coefficients and Mel-frequency Cepstrum Coefficients for Language Identification. Intelligent Multimedia,Video and Speech Processing of 2001 International Symposium on, May 2001: 95～98.
  • 3Rouas J L, Farinas J, Pellegrino F. Modeling Prosody for Language Identification on Read and Spontaneous Speech.Acoustics, Speech and Signal Processing, 2003 (ICASSP'03). IEEE International Conference on, April 2003,6:6～10.
  • 4Jayram A K V S, Ramasubramanian V, Sreenivas T V. Language Identification Using Parallel Sub-word Recognition.Acoustics, Speech and Signal Processing, 2003 (ICASSP'03). 2003 IEEE International Conference on, April 2003, 1:6～10.
  • 5Kohler M A and Kennedy M. Language Identification Using Shifted Delta Cepstra. Circuits and Systems, MWSCAS. The 2002 45th Midwest Symposium on, Aug. 2002, 3: 4～7.
  • 6Qu Dan, Wang Bingxi and Wei Xin. Language Identification Using Vector Quantization. Signal Processing, 2002 6th International Conference on, Aug. 2002, 492～495.

同被引文献7

  • 1Gokhun Tanyer S, Hamza Ozer. Voice activity detection in nonstationary noise[J ]. IEEE Transactions on Speech and Audio Processing, 2000,8(4) :49 - 50.
  • 2Jongseo Sohn, NamSooKim, Sung Wonyong. A statistical model-based voice activity detection[J ]. IEEE Signal Processing Letters, 1999,6(1) :1 - 3.
  • 3Yariv Ephraim, David Malah. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator[ J ]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1984 ,ASSP- 32(6) :1118 - 1121.
  • 4Saeed Gazor, Wei Zhang. Speech probability distribution [ J ] IEEE SignalL Processing Letters, 2003,10(7) : 204 - 207.
  • 5Chang Joon-Hyuk, Nam Soo Kim, Sanjit K. Mitra, life fellow, voice activity detection based on multiple statistical models [ J ]. IEEE Transactions on Signal Processing, 2006,54 (6) : 632 - 634.
  • 6Saeed Gazor, Zhang Wei. A soft voice activity detector based on a laplacian-gaussian model[J ]. IEEE Transactions on Speech and Audio Processing, 2003,11(5) :498 - 505.
  • 7杨行骏,迟惠生.语音信号数字处理[M].北京:电子工业出版社,1995.

引证文献1

二级引证文献1

微电子学与计算机
2004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