Convolutive blind source separation for more than two sources in the frequency domain

Hiroshi Sawada; Ryo Mukai; Shoko Araki; Shoji Makino

doi:10.1250/ast.25.296

Convolutive blind source separation for more than two sources in the frequency domain

Hiroshi Sawada^*, Ryo Mukai, Shoko Araki, Shoji Makino

^*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

The use of blind source separation (BSS) technique for the recovery of more than two sources inthe frequency domain was iprensented. It was found that frequency-domain BSS method was practically applicable for more than two sources by overcoming problem of permutation and circularity. The minimization error could be done by adjusting the scaling ambiguity of the independent component analysis (ICA) solution before windowing. The result shows that the effectiveness and efficiency of the BSS method and the separation of six sources with a planar array of eight sensors.

Original language	English
Pages (from-to)	296-298
Number of pages	3
Journal	Acoustical Science and Technology
Volume	25
Issue number	4
DOIs	https://doi.org/10.1250/ast.25.296
Publication status	Published - 2004 Jul
Externally published	Yes

Keywords

Blind source separation
Convolutive mixtures
Independent component analysis

ASJC Scopus subject areas

Acoustics and Ultrasonics

Access to Document

10.1250/ast.25.296

Cite this

@article{aecc275de58646c890045db29a0e5b96,

title = "Convolutive blind source separation for more than two sources in the frequency domain",

abstract = "The use of blind source separation (BSS) technique for the recovery of more than two sources inthe frequency domain was iprensented. It was found that frequency-domain BSS method was practically applicable for more than two sources by overcoming problem of permutation and circularity. The minimization error could be done by adjusting the scaling ambiguity of the independent component analysis (ICA) solution before windowing. The result shows that the effectiveness and efficiency of the BSS method and the separation of six sources with a planar array of eight sensors.",

keywords = "Blind source separation, Convolutive mixtures, Independent component analysis",

author = "Hiroshi Sawada and Ryo Mukai and Shoko Araki and Shoji Makino",

year = "2004",

month = jul,

doi = "10.1250/ast.25.296",

language = "English",

volume = "25",

pages = "296--298",

journal = "Acoustical Science and Technology",

issn = "1346-3969",

publisher = "Acoustical Society of Japan",

number = "4",

}

TY - JOUR

T1 - Convolutive blind source separation for more than two sources in the frequency domain

AU - Sawada, Hiroshi

AU - Mukai, Ryo

AU - Araki, Shoko

AU - Makino, Shoji

PY - 2004/7

Y1 - 2004/7

N2 - The use of blind source separation (BSS) technique for the recovery of more than two sources inthe frequency domain was iprensented. It was found that frequency-domain BSS method was practically applicable for more than two sources by overcoming problem of permutation and circularity. The minimization error could be done by adjusting the scaling ambiguity of the independent component analysis (ICA) solution before windowing. The result shows that the effectiveness and efficiency of the BSS method and the separation of six sources with a planar array of eight sensors.

AB - The use of blind source separation (BSS) technique for the recovery of more than two sources inthe frequency domain was iprensented. It was found that frequency-domain BSS method was practically applicable for more than two sources by overcoming problem of permutation and circularity. The minimization error could be done by adjusting the scaling ambiguity of the independent component analysis (ICA) solution before windowing. The result shows that the effectiveness and efficiency of the BSS method and the separation of six sources with a planar array of eight sensors.

KW - Blind source separation

KW - Convolutive mixtures

KW - Independent component analysis

UR - http://www.scopus.com/inward/record.url?scp=4344561819&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344561819&partnerID=8YFLogxK

U2 - 10.1250/ast.25.296

DO - 10.1250/ast.25.296

M3 - Article

AN - SCOPUS:4344561819

SN - 1346-3969

VL - 25

SP - 296

EP - 298

JO - Acoustical Science and Technology

JF - Acoustical Science and Technology

IS - 4

ER -

Convolutive blind source separation for more than two sources in the frequency domain

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this