Source separation in strong noisy mixtures: A study of wavelet de-noising pre-processing

This paper addresses the source separation in strong noisy mixtures by wavelet de-noising processing. Experiments include the cases of white/correlated Gaussian and non- Gaussian noise, which correspond to various applications. The performance of BSS/ICA algorithms after wavelet de- noising is quantitatively investigated, and points out the efficiency of the method.

Published in:
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2, null, II/1681-II/1684
Presented at:
Orlando, FL
Swiss Federal Institute of Technol., Lausanne, Switzerland Cited By: 3; Export Date: 14 August 2006; Source: Scopus CODEN: IPROD Language of Original Document: English Correspondence Address: Paraschiv-Ionescu, A.; Swiss Federal Institute of Technol. Lausanne, Switzerland References: Akuzawa, T., New fast factorization method for multivariate optimization and its realization as ICA algorithm'akuzawa; Attias, H., Independent factor analysis (1999) Neural Computation, 11, pp. 803-851; Buckheit, J., Donoho, D.L., Wavelab and reproductible research (1994) Wavelets in Statistics, pp. 55-82, In A. Antoniadis and G. Oppenheim, editors; Cichocki, A., Douglas, S.C., Amari, S., Robust techniques for independent component analysis with noisy data (1998) Neurocomputing, 22, pp. 113-129; Donoho, D.L., Johnstone, I.M., Adapting to unknown smoothness via wavelet shrinkage (1995) J. Am. Statist. Ass., 90, pp. 1200-1244; Donoho, D.L., Yu, T.P.Y., Nonlinear wavelet transforms based on median interpolation http://www-; Hyvarinen, A., Karhunen, J., Oja, E., (2001) Independent Component Analysis, John Wiley & Sons; Mallat, S.G., A theory of multiresolution signal decomposition: The wavelet representation (1989) IEEE Trans. Pattn. Anal. Mach. Intell., 11, pp. 674-693. Sponsors: IEEE
Other identifiers:
View record in Web of Science
Scopus: 2-s2.0-14844324646

 Record created 2006-11-30, last modified 2018-03-17

Rate this document:

Rate this document:
(Not yet reviewed)