Blind source separation based on independent vector analysis using feed-forward network

This paper presents an algorithm that employs a feed-forward (FF) network on each bin as an unmixing system in the framework of independent vector analysis (IVA) to effectively separate highly reverberated mixtures with the exploitation of inter-frequency dependencies of each source signal. Furtherm...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 74; no. 17; pp. 3713 - 3715
Main Authors Oh, Myungwoo, Park, Hyung-Min
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.10.2011
Subjects
Online AccessGet full text

Cover

Loading…
Abstract This paper presents an algorithm that employs a feed-forward (FF) network on each bin as an unmixing system in the framework of independent vector analysis (IVA) to effectively separate highly reverberated mixtures with the exploitation of inter-frequency dependencies of each source signal. Furthermore, to avoid whitening of unmixed source signals due to the use of the FF unmixing network, we derive a learning algorithm for the network based on the extended non-holonomic constraint and the minimal distortion principle. Experiments show that the proposed method delivers better separation performance than the conventional IVA and the FF independent component analysis methods.
AbstractList This paper presents an algorithm that employs a feed-forward (FF) network on each bin as an unmixing system in the framework of independent vector analysis (IVA) to effectively separate highly reverberated mixtures with the exploitation of inter-frequency dependencies of each source signal. Furthermore, to avoid whitening of unmixed source signals due to the use of the FF unmixing network, we derive a learning algorithm for the network based on the extended non-holonomic constraint and the minimal distortion principle. Experiments show that the proposed method delivers better separation performance than the conventional IVA and the FF independent component analysis methods.
Author Oh, Myungwoo
Park, Hyung-Min
Author_xml – sequence: 1
  givenname: Myungwoo
  surname: Oh
  fullname: Oh, Myungwoo
– sequence: 2
  givenname: Hyung-Min
  surname: Park
  fullname: Park, Hyung-Min
  email: hpark@sogang.ac.kr
BookMark eNp9kEtPwzAQhC1UJMrjH3DwkUuC10nt5IIEiJdUiUsljpYfG-SS2sVOWvXfE1TOXHZX2pmR5jsnsxADEnINrAQG4nZdBhxt3JScAZRMlIw1J2QOjeRFwxsxI3PW8kXBK-Bn5DznNWMggbdz8vHQ--BojmOySDNuddKDj4EandHR6ZjeuMVphIHu0A4xUR10f8g-0zH78Ek7RFd0Me11cjTgsI_p65KcdrrPePW3L8jq-Wn1-Fos31_eHu-Xha3ZYiicg9YaIwAaBp3pqqY1llttrLQLZ6wRWFuupauZQ4NSQguiElXdSGQoqwtyc4zdpvg9Yh7UxmeLfa8DxjErEBLqqhELMUnro9SmmHPCTm2T3-h0UMDUL0a1VkeM6hejYkJNGCfb3dGGU4udx6Sy9RgsOp8mGspF_3_AD8aFgXw
CitedBy_id crossref_primary_10_1016_j_neucom_2019_04_030
crossref_primary_10_1016_j_patcog_2023_109376
crossref_primary_10_1016_j_neucom_2015_12_040
crossref_primary_10_1016_j_neucom_2019_07_022
crossref_primary_10_1109_ACCESS_2020_2985842
crossref_primary_10_1007_s11063_017_9741_0
crossref_primary_10_1587_transfun_E98_A_2325
Cites_doi 10.1109/TASL.2006.872618
ContentType Journal Article
Copyright 2011 Elsevier B.V.
Copyright_xml – notice: 2011 Elsevier B.V.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.neucom.2011.06.008
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts

DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 3715
ExternalDocumentID 10_1016_j_neucom_2011_06_008
S092523121100350X
GrantInformation_xml – fundername: National Research Foundation of Korea
  grantid: (No. 2010-0027797
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
29N
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSN
SSV
SSZ
T5K
WUQ
XPP
ZMT
~G-
AAXKI
AAYXX
AFJKZ
AKRWK
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c405t-dd19cbb611801fbf389bc2cabc7c5dbcb6e4c2a7d40debe771916363487e0e73
IEDL.DBID .~1
ISSN 0925-2312
IngestDate Fri Aug 16 22:54:15 EDT 2024
Thu Sep 26 18:45:51 EDT 2024
Fri Feb 23 02:27:16 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 17
Keywords Feed-forward network
Blind source separation
Independent component analysis
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c405t-dd19cbb611801fbf389bc2cabc7c5dbcb6e4c2a7d40debe771916363487e0e73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 1671438656
PQPubID 23500
PageCount 3
ParticipantIDs proquest_miscellaneous_1671438656
crossref_primary_10_1016_j_neucom_2011_06_008
elsevier_sciencedirect_doi_10_1016_j_neucom_2011_06_008
PublicationCentury 2000
PublicationDate 2011-10-01
PublicationDateYYYYMMDD 2011-10-01
PublicationDate_xml – month: 10
  year: 2011
  text: 2011-10-01
  day: 01
PublicationDecade 2010
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2011
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Hyvärinen, Karhunen, Oja (bib2) 2001
Sawada, Mukai, Araki, Makino (bib6) 2001
Araki, Makino, Nishikawa, Saruwatari (bib1) 2001
Kim, Attias, Lee, Lee (bib4) 2007; 15
Matsuoka, Nakashima (bib5) 2001
Kim, Tashev, Acero (bib3) 2010
Kim (10.1016/j.neucom.2011.06.008_bib4) 2007; 15
Hyvärinen (10.1016/j.neucom.2011.06.008_bib2) 2001
Matsuoka (10.1016/j.neucom.2011.06.008_bib5) 2001
Sawada (10.1016/j.neucom.2011.06.008_bib6) 2001
Kim (10.1016/j.neucom.2011.06.008_bib3) 2010
Araki (10.1016/j.neucom.2011.06.008_bib1) 2001
References_xml – volume: 15
  start-page: 70
  year: 2007
  end-page: 79
  ident: bib4
  article-title: Blind source separation exploiting higher-order frequency dependencies
  publication-title: IEEE Transactions on Audio, Speech, and Language Processing
  contributor:
    fullname: Lee
– start-page: 2678
  year: 2010
  end-page: 2681
  ident: bib3
  article-title: Reverberated speech signal separation based on regularized subband feedforward ICA and instantaneous direction of arrival
  publication-title: Proceedings of the ICASSP
  contributor:
    fullname: Acero
– start-page: 722
  year: 2001
  end-page: 727
  ident: bib5
  article-title: Minimal distortion principle for blind source separation
  publication-title: Proceedings of the International Conference on ICA and BSS
  contributor:
    fullname: Nakashima
– year: 2001
  ident: bib2
  article-title: Independent Component Analysis
  contributor:
    fullname: Oja
– start-page: 2737
  year: 2001
  end-page: 2740
  ident: bib1
  article-title: Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech
  publication-title: Proceedings of the ICASSP
  contributor:
    fullname: Saruwatari
– start-page: 663
  year: 2001
  end-page: 668
  ident: bib6
  article-title: A polar-coordinate based activation function for frequency domain blind source separation
  publication-title: Proceedings of the International Conference on ICA and BSS
  contributor:
    fullname: Makino
– year: 2001
  ident: 10.1016/j.neucom.2011.06.008_bib2
  contributor:
    fullname: Hyvärinen
– start-page: 2737
  year: 2001
  ident: 10.1016/j.neucom.2011.06.008_bib1
  article-title: Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech
  contributor:
    fullname: Araki
– start-page: 2678
  year: 2010
  ident: 10.1016/j.neucom.2011.06.008_bib3
  article-title: Reverberated speech signal separation based on regularized subband feedforward ICA and instantaneous direction of arrival
  contributor:
    fullname: Kim
– start-page: 663
  year: 2001
  ident: 10.1016/j.neucom.2011.06.008_bib6
  article-title: A polar-coordinate based activation function for frequency domain blind source separation
  contributor:
    fullname: Sawada
– start-page: 722
  year: 2001
  ident: 10.1016/j.neucom.2011.06.008_bib5
  article-title: Minimal distortion principle for blind source separation
  contributor:
    fullname: Matsuoka
– volume: 15
  start-page: 70
  year: 2007
  ident: 10.1016/j.neucom.2011.06.008_bib4
  article-title: Blind source separation exploiting higher-order frequency dependencies
  publication-title: IEEE Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASL.2006.872618
  contributor:
    fullname: Kim
SSID ssj0017129
Score 2.0563688
Snippet This paper presents an algorithm that employs a feed-forward (FF) network on each bin as an unmixing system in the framework of independent vector analysis...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Publisher
StartPage 3713
SubjectTerms Algorithms
Blind source separation
Blinds
Distortion
Exploitation
Feed-forward network
Independent component analysis
Learning
Networks
Separation
Vector analysis
Title Blind source separation based on independent vector analysis using feed-forward network
URI https://dx.doi.org/10.1016/j.neucom.2011.06.008
https://search.proquest.com/docview/1671438656
Volume 74
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDI6mceHCGzEeU5C4hi19JO1xTEwDxC4MsVvUPIrGoZtYx5HfjpM0k0BCSNyqqq0qO7E_x59thK7KkpqYlwkEOSYhSW4YycArkLxQEIoBhlYuFfM4YePn5H6WzlpoGGphLK2ysf3epjtr3dzpNdLsLefz3lM_jyCKsi3KXHpsZivYwRnBmr7-3NA8KKeR77cXpcQ-HcrnHMerMmvLGfGNPG1WIvvNPf0w1M77jPbQTgMb8cD_2T5qmeoA7YaRDLjZoYfo5QZgo8b-SB6vjO_svaiw9VYaw8V8M_e2xh_uyB4XTWMSbEnwr7gEh0YAy1o-La48TfwITUe30-GYNLMTiAIIVhOtaa6kZLbDGy1lCbhEqkgVUnGVaqkkM4mKCq6TvgY9cg5xG4tZDPGL6RseH6N2tajMCcJxP9JZyUCVyiRUqTwzYBhMyspUKUAIHUSCxMTSd8gQgTr2JryEhZWwcAy6rIN4EKv4pmkBRvyPNy-DFgRsApvZKCqzWK8EZW6MO2DT039__QxtR4HfR89Ru35fmwsAHLXsuhXVRVuDu4fx5AtylddV
link.rule.ids 315,786,790,4521,24144,27957,27958,45620,45714
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5qe9CLb7E-V_C6tEk2u8mxFktqHxcr9rYkm43UQ1ps6u93NpsUFETwFgIJYSY7883Ot98A3GeZoz2RMSxyNKMs1JwGmBVoGCssxRBDq7IVM5ny6IU9zf15A_r1WRhDq6xiv43pZbSu7nQqa3ZWi0XnuRu6WEUZibKyPTbfgRbzhcOa0OoNR9F020wQjmsl91yfmgfqE3QlzSvXG0MbsVqepjER_JahfsTqMgENDmG_Qo6kZz_uCBo6P4aDeioDqRbpCbw-IHJMid2VJ2ttxb2XOTEJKyV4sdiOvi3IZ7lrT-JKm4QYHvwbyTCnUYSzhlJLcssUP4XZ4HHWj2g1PoEqRGEFTVMnVEnCjcibkyUZQpNEuSpOlFB-mqiEa6bcWKSsm6IrhcDSjXvcwxJGd7XwzqCZL3N9DsTrummQcfSm0sxRKgw0xgbt88xXCkFCG2htMbmyIhmyZo-9S2thaSwsSxJd0AZRm1V-c7bEOP7Hk3e1FySuA9PciHO93Kylw8tJ7ghPL_799lvYjWaTsRwPp6NL2HNrup9zBc3iY6OvEX8UyU31f30B50zaCw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Blind+source+separation+based+on+independent+vector+analysis+using+feed-forward+network&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Oh%2C+Myungwoo&rft.au=Park%2C+Hyung-Min&rft.date=2011-10-01&rft.issn=0925-2312&rft.volume=74&rft.issue=17&rft.spage=3713&rft.epage=3715&rft_id=info:doi/10.1016%2Fj.neucom.2011.06.008&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2011_06_008
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon