A general algebraic algorithm for blind extraction of one source in a MIMO convolutive mixture

Rémi Dubroca; Christophe De Luigi; Marc Castella; Eric Moreau

doi:10.1109/TSP.2010.2042487

A general algebraic algorithm for blind extraction of one source in a MIMO convolutive mixture

Rémi Dubroca, Christophe De Luigi, Marc Castella, Eric Moreau

Research output: Contribution to journal › Article › peer-review

Abstract

The paper deals with the problem of blind source extraction from a multiple-input/multiple-output (MIMO) convolutive mixture. We define a new criterion for source extraction which uses higher-order contrast functions based on so called reference signals. It generalizes existing reference-based contrasts. In order to optimize the new criterion, we propose a general algebraic algorithm based on best rank-1 tensor approximation. Computer simulations illustrate the good behavior and the interest of our algorithm in comparison with other approaches.

Original language	English
Article number	5406145
Pages (from-to)	2484-2493
Number of pages	10
Journal	IEEE Transactions on Signal Processing
Volume	58
Issue number	5
DOIs	https://doi.org/10.1109/TSP.2010.2042487
Publication status	Published - 1 May 2010
Externally published	Yes

Keywords

Blind source extraction
Contrast functions
Higher-order statistics
Independent component analysis
Tensor decomposition

Access to Document

10.1109/TSP.2010.2042487

Cite this

@article{995fdb01aaf748efa78d0eb223b0d3b9,

title = "A general algebraic algorithm for blind extraction of one source in a MIMO convolutive mixture",

abstract = "The paper deals with the problem of blind source extraction from a multiple-input/multiple-output (MIMO) convolutive mixture. We define a new criterion for source extraction which uses higher-order contrast functions based on so called reference signals. It generalizes existing reference-based contrasts. In order to optimize the new criterion, we propose a general algebraic algorithm based on best rank-1 tensor approximation. Computer simulations illustrate the good behavior and the interest of our algorithm in comparison with other approaches.",

keywords = "Blind source extraction, Contrast functions, Higher-order statistics, Independent component analysis, Tensor decomposition",

author = "R{\'e}mi Dubroca and \{De Luigi\}, Christophe and Marc Castella and Eric Moreau",

year = "2010",

month = may,

day = "1",

doi = "10.1109/TSP.2010.2042487",

language = "English",

volume = "58",

pages = "2484--2493",

journal = "IEEE Transactions on Signal Processing",

issn = "1053-587X",

number = "5",

}

TY - JOUR

T1 - A general algebraic algorithm for blind extraction of one source in a MIMO convolutive mixture

AU - Dubroca, Rémi

AU - De Luigi, Christophe

AU - Castella, Marc

AU - Moreau, Eric

PY - 2010/5/1

Y1 - 2010/5/1

N2 - The paper deals with the problem of blind source extraction from a multiple-input/multiple-output (MIMO) convolutive mixture. We define a new criterion for source extraction which uses higher-order contrast functions based on so called reference signals. It generalizes existing reference-based contrasts. In order to optimize the new criterion, we propose a general algebraic algorithm based on best rank-1 tensor approximation. Computer simulations illustrate the good behavior and the interest of our algorithm in comparison with other approaches.

AB - The paper deals with the problem of blind source extraction from a multiple-input/multiple-output (MIMO) convolutive mixture. We define a new criterion for source extraction which uses higher-order contrast functions based on so called reference signals. It generalizes existing reference-based contrasts. In order to optimize the new criterion, we propose a general algebraic algorithm based on best rank-1 tensor approximation. Computer simulations illustrate the good behavior and the interest of our algorithm in comparison with other approaches.

KW - Blind source extraction

KW - Contrast functions

KW - Higher-order statistics

KW - Independent component analysis

KW - Tensor decomposition

U2 - 10.1109/TSP.2010.2042487

DO - 10.1109/TSP.2010.2042487

M3 - Article

AN - SCOPUS:77951189317

SN - 1053-587X

VL - 58

SP - 2484

EP - 2493

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

IS - 5

M1 - 5406145

ER -

A general algebraic algorithm for blind extraction of one source in a MIMO convolutive mixture

Abstract

Keywords

Access to Document

Fingerprint

Cite this