An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems

Alfred Mertins; Iain Russel

doi:10.1109/ISSPA.2003.1224930

An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems

Alfred Mertins, Iain Russel

Institute of Signal Processing

University of Wollongong

1 Citation (Scopus)

Abstract

This paper presents an extension of the ACDC algorithm introduced by Yeredor for the instantaneous mixing problem to the more general convolutive mixing problem with non-white sources. Further assumptions made on the source signals are their mutual statistical independence, nonstationarity and smoothness of their power spectra. The algorithm iterates the estimation of the mixing system (AC step) and the source statistics (DC step) until convergence is achieved. The proposed algorithm operates in the frequency domain, but unlike most frequency domain algorithms, it carries out some of the operations jointly for all frequencies. This allows us to overcome frequency dependent permutation and scaling problems.

Original language	English
Title of host publication	Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings
Number of pages	4
Publisher	IEEE
Publication date	01.01.2003
Pages	527-530
Article number	1224930
ISBN (Print)	0-7803-7946-2
DOIs	https://doi.org/10.1109/ISSPA.2003.1224930
Publication status	Published - 01.01.2003
Event	7th International Symposium on Signal Processing and Its Applications - Paris, France Duration: 01.07.2003 → 04.07.2003 Conference number: 106263

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1109/ISSPA.2003.1224930

Cite this

@inproceedings{da28a991ffb544d188dd731c424a9442,

title = "An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems",

abstract = "This paper presents an extension of the ACDC algorithm introduced by Yeredor for the instantaneous mixing problem to the more general convolutive mixing problem with non-white sources. Further assumptions made on the source signals are their mutual statistical independence, nonstationarity and smoothness of their power spectra. The algorithm iterates the estimation of the mixing system (AC step) and the source statistics (DC step) until convergence is achieved. The proposed algorithm operates in the frequency domain, but unlike most frequency domain algorithms, it carries out some of the operations jointly for all frequencies. This allows us to overcome frequency dependent permutation and scaling problems.",

author = "Alfred Mertins and Iain Russel",

year = "2003",

month = jan,

day = "1",

doi = "10.1109/ISSPA.2003.1224930",

language = "English",

isbn = "0-7803-7946-2",

series = "IEEE Proceedings",

publisher = "IEEE",

pages = "527--530",

booktitle = "Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings",

note = "7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 ; Conference date: 01-07-2003 Through 04-07-2003",

}

Mertins, A & Russel, I 2003, An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems. in Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings., 1224930, IEEE Proceedings, IEEE, pp. 527-530, 7th International Symposium on Signal Processing and Its Applications, Paris, France, 01.07.03. https://doi.org/10.1109/ISSPA.2003.1224930

TY - GEN

T1 - An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems

AU - Mertins, Alfred

AU - Russel, Iain

N1 - Conference code: 106263

PY - 2003/1/1

Y1 - 2003/1/1

N2 - This paper presents an extension of the ACDC algorithm introduced by Yeredor for the instantaneous mixing problem to the more general convolutive mixing problem with non-white sources. Further assumptions made on the source signals are their mutual statistical independence, nonstationarity and smoothness of their power spectra. The algorithm iterates the estimation of the mixing system (AC step) and the source statistics (DC step) until convergence is achieved. The proposed algorithm operates in the frequency domain, but unlike most frequency domain algorithms, it carries out some of the operations jointly for all frequencies. This allows us to overcome frequency dependent permutation and scaling problems.

AB - This paper presents an extension of the ACDC algorithm introduced by Yeredor for the instantaneous mixing problem to the more general convolutive mixing problem with non-white sources. Further assumptions made on the source signals are their mutual statistical independence, nonstationarity and smoothness of their power spectra. The algorithm iterates the estimation of the mixing system (AC step) and the source statistics (DC step) until convergence is achieved. The proposed algorithm operates in the frequency domain, but unlike most frequency domain algorithms, it carries out some of the operations jointly for all frequencies. This allows us to overcome frequency dependent permutation and scaling problems.

UR - https://www.scopus.com/pages/publications/84904302686

U2 - 10.1109/ISSPA.2003.1224930

DO - 10.1109/ISSPA.2003.1224930

M3 - Conference contribution

SN - 0-7803-7946-2

T3 - IEEE Proceedings

SP - 527

EP - 530

BT - Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings

PB - IEEE

T2 - 7th International Symposium on Signal Processing and Its Applications

Y2 - 1 July 2003 through 4 July 2003

ER -

An extended ACDC Algorithm for the Blind Estimation of Convolutive Mixing Systems

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this