Solving the Permutation Problem in Convolutive Blind Source Separation

Radoslaw Mazur; Alfred Mertins

doi:10.1007/978-3-540-74494-8_64

Solving the Permutation Problem in Convolutive Blind Source Separation

Institut für Signalverarbeitung

Abstract

This paper presents a new algorithm for solving the permutation ambiguity in convolutive blind source separation. When transformed to the frequency domain, the source separation problem reduces to independent instantaneous separation in each frequency bin, which can be efficiently solved by existing algorithms. But this independency leads to the problem of correct alignment of these single bins which is still not entirely solved. The algorithm proposed in this paper models the frequency-domain separated signals using the generalized Gaussian distribution and utilizes the small deviation of the exponent between neighboring bins for the detection of correct permutations.

Originalsprache	Englisch
Titel	Independent Component Analysis and Signal Separation
Redakteure/-innen	Mike E. Davies, Christopher J. James, Samer A. Abdallah, Mark D. Plumbley
Seitenumfang	8
Band	4666 LNCS
Erscheinungsort	Berlin, Heidelberg
Herausgeber (Verlag)	Springer Berlin Heidelberg
Erscheinungsdatum	01.09.2007
Seiten	512-519
ISBN (Print)	978-3-540-74493-1
ISBN (elektronisch)	978-3-540-74494-8
DOIs	https://doi.org/10.1007/978-3-540-74494-8_64
Publikationsstatus	Veröffentlicht - 01.09.2007
Veranstaltung	7th International Conference on Independent Component Analysis (ICA) and Source Separation - London, Großbritannien / Vereinigtes Königreich Dauer: 09.09.2007 → 12.09.2007 Konferenznummer: 70941

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Dokumente

10.1007/978-3-540-74494-8_64

Weitere Links

https://www.scopus.com/record/display.uri?eid=2-s2.0-38149021538&origin=inward&txGid=09b9f3c957f64330764fd48e69c565e7

Blinde Separierung akustischer Quellensignale in reflexionsbehafteter Umgebung
Mertins, A. (Projektleiter*in (PI)) & Kollmeier, B. (Beteiligte Person)
01.01.04 → 31.12.08
Projekt: DFG-Projekte › DFG Einzelförderungen

Zitieren

Mazur, R., & Mertins, A. (2007). Solving the Permutation Problem in Convolutive Blind Source Separation. in M. E. Davies, C. J. James, S. A. Abdallah, & M. D. Plumbley (Hrsg.), Independent Component Analysis and Signal Separation (Band 4666 LNCS, S. 512-519). (Lecture Notes in Computer Science; Band 4666 LNCS). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-74494-8_64

@inproceedings{cf6a5b7860554ab4ac3587b77311f1b5,

title = "Solving the Permutation Problem in Convolutive Blind Source Separation",

abstract = "This paper presents a new algorithm for solving the permutation ambiguity in convolutive blind source separation. When transformed to the frequency domain, the source separation problem reduces to independent instantaneous separation in each frequency bin, which can be efficiently solved by existing algorithms. But this independency leads to the problem of correct alignment of these single bins which is still not entirely solved. The algorithm proposed in this paper models the frequency-domain separated signals using the generalized Gaussian distribution and utilizes the small deviation of the exponent between neighboring bins for the detection of correct permutations.",

author = "Radoslaw Mazur and Alfred Mertins",

year = "2007",

month = sep,

day = "1",

doi = "10.1007/978-3-540-74494-8_64",

language = "English",

isbn = "978-3-540-74493-1",

volume = "4666 LNCS",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "512--519",

editor = "Davies, {Mike E.} and James, {Christopher J.} and Abdallah, {Samer A.} and Plumbley, {Mark D.}",

booktitle = "Independent Component Analysis and Signal Separation",

note = "7th International Conference on Independent Component Analysis (ICA) and Source Separation, ICA 2007 ; Conference date: 09-09-2007 Through 12-09-2007",

}

Mazur, R & Mertins, A 2007, Solving the Permutation Problem in Convolutive Blind Source Separation. in ME Davies, CJ James, SA Abdallah & MD Plumbley (Hrsg.), Independent Component Analysis and Signal Separation. Bd. 4666 LNCS, Lecture Notes in Computer Science, Bd. 4666 LNCS, Springer Berlin Heidelberg, Berlin, Heidelberg, S. 512-519, 7th International Conference on Independent Component Analysis (ICA) and Source Separation, London, Großbritannien / Vereinigtes Königreich, 09.09.07. https://doi.org/10.1007/978-3-540-74494-8_64

Solving the Permutation Problem in Convolutive Blind Source Separation. / Mazur, Radoslaw; Mertins, Alfred.
Independent Component Analysis and Signal Separation. Hrsg. / Mike E. Davies; Christopher J. James; Samer A. Abdallah; Mark D. Plumbley. Band 4666 LNCS Berlin, Heidelberg: Springer Berlin Heidelberg, 2007. S. 512-519 (Lecture Notes in Computer Science; Band 4666 LNCS).

Publikation: Kapitel in Büchern/Berichten/Konferenzbänden › Konferenzbeitrag › Begutachtung

TY - GEN

T1 - Solving the Permutation Problem in Convolutive Blind Source Separation

AU - Mazur, Radoslaw

AU - Mertins, Alfred

N1 - Conference code: 70941

PY - 2007/9/1

Y1 - 2007/9/1

N2 - This paper presents a new algorithm for solving the permutation ambiguity in convolutive blind source separation. When transformed to the frequency domain, the source separation problem reduces to independent instantaneous separation in each frequency bin, which can be efficiently solved by existing algorithms. But this independency leads to the problem of correct alignment of these single bins which is still not entirely solved. The algorithm proposed in this paper models the frequency-domain separated signals using the generalized Gaussian distribution and utilizes the small deviation of the exponent between neighboring bins for the detection of correct permutations.

AB - This paper presents a new algorithm for solving the permutation ambiguity in convolutive blind source separation. When transformed to the frequency domain, the source separation problem reduces to independent instantaneous separation in each frequency bin, which can be efficiently solved by existing algorithms. But this independency leads to the problem of correct alignment of these single bins which is still not entirely solved. The algorithm proposed in this paper models the frequency-domain separated signals using the generalized Gaussian distribution and utilizes the small deviation of the exponent between neighboring bins for the detection of correct permutations.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-38149021538&origin=inward&txGid=09b9f3c957f64330764fd48e69c565e7

U2 - 10.1007/978-3-540-74494-8_64

DO - 10.1007/978-3-540-74494-8_64

M3 - Conference contribution

SN - 978-3-540-74493-1

VL - 4666 LNCS

T3 - Lecture Notes in Computer Science

SP - 512

EP - 519

BT - Independent Component Analysis and Signal Separation

A2 - Davies, Mike E.

A2 - James, Christopher J.

A2 - Abdallah, Samer A.

A2 - Plumbley, Mark D.

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - 7th International Conference on Independent Component Analysis (ICA) and Source Separation

Y2 - 9 September 2007 through 12 September 2007

ER -

Solving the Permutation Problem in Convolutive Blind Source Separation

Abstract

UN SDGs

Dokumente

Weitere Links

Fingerprint

Projekte

Blinde Separierung akustischer Quellensignale in reflexionsbehafteter Umgebung

Zitieren