Blind source separation based on time-domain optimization of a frequency-domain independence criterion

Tiemin Mei; Jiangtao Xi; Fuliang Yin; Alfred Mertins; Joe F. Chicharo

doi:10.1109/TASL.2006.872623

Blind source separation based on time-domain optimization of a frequency-domain independence criterion

Tiemin Mei^*, Jiangtao Xi, Fuliang Yin, Alfred Mertins, Joe F. Chicharo

^*Corresponding author for this work

Institute of Signal Processing

27 Citations (Scopus)

Abstract

A new technique for the blind separation of convolutive mixtures is proposed in this paper. Inspired by the works of Amari, Sabala , and Rahbar, we firstly start from the application of Kullback-Leibler divergence in frequency domain, and then we integrate Kullback-Leibler divergence over the whole frequency range of interest to yield a new objective function which turns out to be time-domain variable dependent. In other words, the objective function is derived in frequency domain which can be optimized with respect to time domain variables. The proposed technique has the advantages of frequency domain approaches and is suitable for very long mixing channels, but does not suffer from the local permutation problem as the separation is achieved in time-domain

Original language	English
Article number	1709896
Journal	IEEE Transactions on Audio, Speech and Language Processing
Volume	14
Issue number	6
Pages (from-to)	2075-2085
Number of pages	11
ISSN	1558-7916
DOIs	https://doi.org/10.1109/TASL.2006.872623
Publication status	Published - 01.11.2006

Funding

Manuscript received February 16, 2005; revised October 6, 2005. This work was supported in part by the National Natural Science Foundation of China under Grant 60172073 and Grant 60372082, and the Trans-Century Training Program Foundation for the Talents by the Ministry of Education of China and in part by the Australia Research Council under ARC large Grant A00103052, and in part by the German Research Foundation under Grant ME1170/1. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Hong-Goo Kang.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TASL.2006.872623

Cite this

@article{dfe2e480a8254a9f9c154131beba626e,

title = "Blind source separation based on time-domain optimization of a frequency-domain independence criterion",

abstract = "A new technique for the blind separation of convolutive mixtures is proposed in this paper. Inspired by the works of Amari, Sabala , and Rahbar, we firstly start from the application of Kullback-Leibler divergence in frequency domain, and then we integrate Kullback-Leibler divergence over the whole frequency range of interest to yield a new objective function which turns out to be time-domain variable dependent. In other words, the objective function is derived in frequency domain which can be optimized with respect to time domain variables. The proposed technique has the advantages of frequency domain approaches and is suitable for very long mixing channels, but does not suffer from the local permutation problem as the separation is achieved in time-domain",

author = "Tiemin Mei and Jiangtao Xi and Fuliang Yin and Alfred Mertins and Chicharo, \{Joe F.\}",

year = "2006",

month = nov,

day = "1",

doi = "10.1109/TASL.2006.872623",

language = "English",

volume = "14",

pages = "2075--2085",

journal = "IEEE Transactions on Audio, Speech and Language Processing",

issn = "1558-7916",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Blind source separation based on time-domain optimization of a frequency-domain independence criterion

AU - Mei, Tiemin

AU - Xi, Jiangtao

AU - Yin, Fuliang

AU - Mertins, Alfred

AU - Chicharo, Joe F.

PY - 2006/11/1

Y1 - 2006/11/1

N2 - A new technique for the blind separation of convolutive mixtures is proposed in this paper. Inspired by the works of Amari, Sabala , and Rahbar, we firstly start from the application of Kullback-Leibler divergence in frequency domain, and then we integrate Kullback-Leibler divergence over the whole frequency range of interest to yield a new objective function which turns out to be time-domain variable dependent. In other words, the objective function is derived in frequency domain which can be optimized with respect to time domain variables. The proposed technique has the advantages of frequency domain approaches and is suitable for very long mixing channels, but does not suffer from the local permutation problem as the separation is achieved in time-domain

AB - A new technique for the blind separation of convolutive mixtures is proposed in this paper. Inspired by the works of Amari, Sabala , and Rahbar, we firstly start from the application of Kullback-Leibler divergence in frequency domain, and then we integrate Kullback-Leibler divergence over the whole frequency range of interest to yield a new objective function which turns out to be time-domain variable dependent. In other words, the objective function is derived in frequency domain which can be optimized with respect to time domain variables. The proposed technique has the advantages of frequency domain approaches and is suitable for very long mixing channels, but does not suffer from the local permutation problem as the separation is achieved in time-domain

UR - https://www.scopus.com/pages/publications/34248678349

U2 - 10.1109/TASL.2006.872623

DO - 10.1109/TASL.2006.872623

M3 - Journal articles

AN - SCOPUS:34248678349

SN - 1558-7916

VL - 14

SP - 2075

EP - 2085

JO - IEEE Transactions on Audio, Speech and Language Processing

JF - IEEE Transactions on Audio, Speech and Language Processing

IS - 6

M1 - 1709896

ER -

Blind source separation based on time-domain optimization of a frequency-domain independence criterion

Abstract

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Blind separation of acoustic source signals in a reflective environment

Cite this

Blind source separation based on time-domain optimization of a frequency-domain independence criterion

Abstract

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

Blind separation of acoustic source signals in a reflective environment

Cite this