Mutual information minimization for under-determined blind source separation

Fuxiang Wang; Jun Zhang

doi:10.1109/CISE.2009.5365757

Mutual information minimization for under-determined blind source separation

Fuxiang Wang^*, Jun Zhang

^*Corresponding author for this work

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

An important step of sparse representation technique for under-determined BSS (Blind Source Separation) is the estimation of the mixing matrix. In this paper, a new method to estimate the mixing matrix is proposed. The objective is to find the mixing matrix to minimize the mutual information of the estimated sources. An algorithm for the learning of the mixing matrix is proposed by the natural gradient. Simulation results of speech separation demonstrate the effectiveness of our method.

Original language	English
Title of host publication	Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009
DOIs	https://doi.org/10.1109/CISE.2009.5365757
Publication status	Published - 2009
Externally published	Yes
Event	2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009 - Wuhan, China Duration: 11 Dec 2009 → 13 Dec 2009

Publication series

Name	Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009

Conference

Conference	2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009
Country/Territory	China
City	Wuhan
Period	11/12/09 → 13/12/09

Keywords

Mutual information
Sparse representation
Under-determined blind source separation

Access to Document

10.1109/CISE.2009.5365757

Cite this

Wang, F., & Zhang, J. (2009). Mutual information minimization for under-determined blind source separation. In Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009 Article 5365757 (Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009). https://doi.org/10.1109/CISE.2009.5365757

@inproceedings{58c8e276d23d4af1a13902f823bd8f9a,

title = "Mutual information minimization for under-determined blind source separation",

abstract = "An important step of sparse representation technique for under-determined BSS (Blind Source Separation) is the estimation of the mixing matrix. In this paper, a new method to estimate the mixing matrix is proposed. The objective is to find the mixing matrix to minimize the mutual information of the estimated sources. An algorithm for the learning of the mixing matrix is proposed by the natural gradient. Simulation results of speech separation demonstrate the effectiveness of our method.",

keywords = "Mutual information, Sparse representation, Under-determined blind source separation",

author = "Fuxiang Wang and Jun Zhang",

year = "2009",

doi = "10.1109/CISE.2009.5365757",

language = "English",

isbn = "9781424445073",

series = "Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009",

booktitle = "Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009",

note = "2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009 ; Conference date: 11-12-2009 Through 13-12-2009",

}

Wang, F & Zhang, J 2009, Mutual information minimization for under-determined blind source separation. in Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009., 5365757, Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009, 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009, Wuhan, China, 11/12/09. https://doi.org/10.1109/CISE.2009.5365757

Mutual information minimization for under-determined blind source separation. / Wang, Fuxiang; Zhang, Jun.
Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009. 2009. 5365757 (Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Mutual information minimization for under-determined blind source separation

AU - Wang, Fuxiang

AU - Zhang, Jun

PY - 2009

Y1 - 2009

N2 - An important step of sparse representation technique for under-determined BSS (Blind Source Separation) is the estimation of the mixing matrix. In this paper, a new method to estimate the mixing matrix is proposed. The objective is to find the mixing matrix to minimize the mutual information of the estimated sources. An algorithm for the learning of the mixing matrix is proposed by the natural gradient. Simulation results of speech separation demonstrate the effectiveness of our method.

AB - An important step of sparse representation technique for under-determined BSS (Blind Source Separation) is the estimation of the mixing matrix. In this paper, a new method to estimate the mixing matrix is proposed. The objective is to find the mixing matrix to minimize the mutual information of the estimated sources. An algorithm for the learning of the mixing matrix is proposed by the natural gradient. Simulation results of speech separation demonstrate the effectiveness of our method.

KW - Mutual information

KW - Sparse representation

KW - Under-determined blind source separation

UR - http://www.scopus.com/inward/record.url?scp=77949743457&partnerID=8YFLogxK

U2 - 10.1109/CISE.2009.5365757

DO - 10.1109/CISE.2009.5365757

M3 - Conference contribution

AN - SCOPUS:77949743457

SN - 9781424445073

T3 - Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009

BT - Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009

T2 - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009

Y2 - 11 December 2009 through 13 December 2009

ER -

Mutual information minimization for under-determined blind source separation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this