基于MVDR参数谱特征提取的语音识别被引量：1

下载PDF

导出

摘要介绍了最小方差无失真响应建模方法,并与线性预测方法进行了比较,比较发现最小方差无失真响应滤波器能提供一个更好的原始语音包络。进而将MVDR参数提取方法应用于ICA中,并与基于传统LP的ICA方法的语音识别性能进行了比较,对结果进行了分析。

作者吴名钊马震李建磊陈延萍

机构地区滨州学院计算机科学系山东移动滨州分公司

出处《声学与电子工程》 2009年第2期28-30,共3页 Acoustics and Electronics Engineering

关键词语音识别最小方差无失真响应独立分量分析

参考文献6

1杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报,2002,28(5):762-772. 被引量：148
2P J Sherman, K-N Lou. On the family of ML spectral estimatesfor mixed spectrum identification[J]. IEEE Trans. Signal Processing, 1991,39: 644-655.
3S Haykin. Adaptive Filter Theory[M]. NJ: Prentice Hall, 1991.
4马震,陈延萍.最小方差无失真响应浊音谱建模方法研究[J].应用声学,2008,27(4):326-332. 被引量：3
5S L Marple Jr. Digital Spectral Analysis with Applications[M]. NJ: Prentice-Hall, 1987.
6Lee Te-Won. Independent Component Analysis: Theory and Applications[M]. Boston: Kluwer Academic Publishers, 1998.

1孙即祥.数字图像处理[M].石家庄:河北教育出版社,1993..
2焦李成.神经网络的应用与实现[M].西安:西安电子科技大学出版社,1996..
3章照止林须端.信息论与最优编码[M].上海:上海科学技术出版社,1993..
4A. El-Jaroudi and J. Makhoul. Discrete all-pole modeling,. IEEE Trans. Signal Processing, Feb. 1991,vol. 39:411 - 423.
5M. Oudot, O. Cappe, and E. Moulines. Robust estimation of the spectral envelope for harmonics + noise models. IEEE Workshop Speech Coding Telecommunications Proceedings, 1997.
6P. J Sherman and K. -N. Lou. On the family of ML spectral estimates for mixed spectrum identification. IEEE Trans. Signal Processing, Mar. 1991 ,vol. 39:644 -655.
7S. Haykin Adaptive Filter Theory. Englewood Cliffs, NJ: Prentice Hall, 1991:273 - 285.
8S. L. Marple, Jr. Digital Spectral Analysis with Applications. Englewood Cliffs, NJ: Prentice-Hall, 1987:159- 172.
9Sayed A. H. , Kailath T. A survey of spectral factorization methods. Numerical Linear Algebra with Applications,2001, 08 : 467 - 496.

1侯雪梅,张雪英,赵高峰.一种改进的基于LP倒谱特征的孤立词语音识别方法[J].太原理工大学学报,2006,37(5):508-510. 被引量：2
2Manohar N Murthi, Bhaskar D Rao. All-Pole Model ing of Speech Based on the Minimum Variance Disor- tionless Response Spectrum[J]. IEEE Transactions on Speech and Audio Processing. 2000, 8 (3) : 221- 239.
3Manohar N Murthi, Bhasker D Rao. All pole model parameter estimation for voice speech [C]//Proc. IEEE Workshop on Speech Coding for Telecommunica- tion. Pennsylvania, USA: IEEE, 1997:17 -18.
4Manohar N Murthi, Bhaskar D Rao. All-Pole Model- ing of Speech Based on the Minimum Variance Distor tionless Response Spectrum [C]//Signals, Systems 8< Computers, Conference Record of the Thirty-First A silomar Conference. Pacific Grove, California: IEEE, 1997:1061-1065.
5曾庆军,王菲,黄国建.基于连续谱特征提取的被动声纳目标识别技术[J].上海交通大学学报,2002,36(3):382-386. 被引量：23

声学与电子工程

2009年第2期

内容加载中请稍等...