Wavelet Based Multi - Scale Principal Component Analysis for Speech Enhancement

  ijett-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
© 2012 by IJETT Journal
Volume-3 Issue-3                          
Year of Publication : 2012
Authors :  Mr. Vijaykumar D. Shinde , Mr. C. G. Patil , Mr. Sachin D. Ruikar


Mr. Vijaykumar D. Shinde , Mr. C. G. Patil , Mr. Sachin D. Ruikar. "Wavelet Based Multi - Scale Principal Component Analysis for Speech Enhancement". International Journal of Engineering Trends and Technology (IJETT). V3(3):397-400 May-Jun 2012. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group


The goal of speech enhancement varies according to specific applications, such as to reduce listener fatigue, to boost the overall speech quality, to incre ase intelligibility, and to improve the performance of the voice communication device. This paper presents M ultiscale principal component analysis (MSPCA) for denoising of single channel speech signal. Principle Component Analysis ( PCA ) is a standard tool in modern data analysis because it is simple method for extracting relevant information from complex data matrix using eigenvalues and eigenvectors . The multiscale principal component generalizes the usual PCA of a multivariate signal seen as a matrix by performing simultaneously a PCA on the matrices of details of different levels. In multi scale Principal Component Analysis (MSPCA) decorrelate the variables by ext racting a linear relati onship and wavelet analysis . In addition, a PCA is performed also on the coarser approximation coefficients matrix in the wavelet domain as well as on the final reconstructed matrix. By selecting conveniently the numbers of retained principal components, interesting simplified signals can be reconstructed Wavelet analysis of speech signal segments the voice information content at different Wavelet scales. At subband levels or scales multivariate data matrix are formed using Wavelet co efficients extracted from the same scales of voice signals. At each subband matrix or scales, PCA is used for noise reduction . Qualitative performance is evaluated and quantitative performance of denoising effect is measured by input/output signal - to - noise ratio (SNR) , segmental SNR and IS measure .


[1] Abolhassani, Amin Haji / Selouani, Sid - Ahmed / O`Shaughnessy, Douglas / Harkat, Mohamed - Faouzi (2007), "Speech enhancement using PCA and variance of the reconstruction error model identification", In INTERSPEECH - 2007 , 974 - 977.
[2] Tetsuya Takiguchi, Yasuo Ariki . (2007) , “ PCA - Based Speech Enhancement for Distorted Speech Recognition” Journal of Multimedia , Vol 2, No 5 , 13 - 18, Sep 2007
[3] Aminghafari, M.; Cheze, N.; Poggi, J - M. (2006), "Multivariate de - noising using wavelets and principal component analysis," Computational Statistics & Data Analysis, 50, pp. 2381 - 2398.
[4] Jonathon Shlens (2005) , "A Tutorial on Principal Component Analysis", Systems Neurobiology Laboratory, Salk Institute for Biological Studies La Jolla, CA92037 and Institute for Nonlinear S cience, University of California, San Diego La Jolla, CA 92093 - 0402 .
[5] Chang, S., Y.Kwon (2002). Speech enhancement for non - stationary noise enviro n ment by adaptive wavelet packet. International conference on audio,speech and signal processing of IEEE.
[6] Bahoura, M. a. J. R. (2001). "Wavelet speech enhancement based on the Teager engergy operator." IEEE Signal Processing Letters 8 (1): 10 - 12.
[7] S. Valle, W. Li and S.J. Qin (1999) , “Selection of the number of principal components: the variance of t he reconstruction error criterion with a comparison to other methods”, Industrial and Engineering Chemistry Research 38 , pp. 43894401.
[8] Rousseeuw, P.; Van Driessen, K. (1999), "A fast algorithm for the minimum covariance determinant estimator," Technometrics, 41, pp. 212 - 223.
[9] Bakshi, B. (1998), "Multiscale PCA with application to MSPC monitoring," AIChE J., 44, pp. 1596 - 1610.
[10] Qin, S. J.; Dunia R. (1998), Determining the number of principal components for best r econstruction. In IFAC DYCOPS’98 , Greece, June 1998.
[11] Seok, J. W. (1997). Speech enhancement with reduction of noise components in the wavelet domain. International conference on audio,speech and signal processing of IEEE.
[12] Sheikhzadeh, H. (2001). An improved wavelet - based speech enhancement system. Eurospeech.
[13] Donoho, D. L. (1995). "Denosing by soft thresholding." IEEE Trans. on Information Theory 41 (3): 613 - 627.

Multiscale Principal Component Analysis (MSPCA), Principal component Analysis (PCA), Speech Enhancement , Signal Denoising , Wavelet Analysis .