On the indeterminacies of convolutive blind signal separation based on second-order statistics

D.W.E. Schobben; P.C.W. Sommen

On the indeterminacies of convolutive blind signal separation based on second-order statistics

D.W.E. Schobben, P.C.W. Sommen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

124 Downloads (Pure)

Abstract

Recently, several blind signal separation algorithms have been developed which are based on second order statistics. Little has been published however on whether second order statistics are sufficient to obtain a unique solution. Especially for applications that involve convolutive mixing and unmixing of signals that are correlated in time, there is a lack of knowledge on why and in what cases second order statistics suffice. This paper investigates the indeterminacies that are introduced when second order statistics are used and presents a theorem for the unmixing system to be uniquely found using second order statistics.

Original language	English
Title of host publication	Proc. ISSPA '99, Fifth International Symposium on Signal Processing and its Applications
Editors	M. Deriche, B. Boashash, W.W. Boles
Place of Publication	Brisbane, QLD, Australia
Publisher	Queensland University of Technology
Pages	215-218
ISBN (Print)	1 86435 451 8
Publication status	Published - 1999
Event	ISSPA '99, Fifth International Symposium on Signal Processing and its Applications - Brisbane, Australia Duration: 22 Aug 1999 → 25 Aug 1999

Conference

Conference	ISSPA '99, Fifth International Symposium on Signal Processing and its Applications
Country/Territory	Australia
City	Brisbane
Period	22/08/99 → 25/08/99

Access to Document

599728671256613Final author version , 55.6 KB

Cite this

@inproceedings{0c8e0d70f88c49bea91eff2754c6114e,

title = "On the indeterminacies of convolutive blind signal separation based on second-order statistics",

abstract = "Recently, several blind signal separation algorithms have been developed which are based on second order statistics. Little has been published however on whether second order statistics are sufficient to obtain a unique solution. Especially for applications that involve convolutive mixing and unmixing of signals that are correlated in time, there is a lack of knowledge on why and in what cases second order statistics suffice. This paper investigates the indeterminacies that are introduced when second order statistics are used and presents a theorem for the unmixing system to be uniquely found using second order statistics.",

author = "D.W.E. Schobben and P.C.W. Sommen",

year = "1999",

language = "English",

isbn = "1 86435 451 8",

pages = "215--218",

editor = "M. Deriche and B. Boashash and W.W. Boles",

booktitle = "Proc. ISSPA '99, Fifth International Symposium on Signal Processing and its Applications",

publisher = "Queensland University of Technology",

note = "ISSPA '99, Fifth International Symposium on Signal Processing and its Applications ; Conference date: 22-08-1999 Through 25-08-1999",

}

Schobben, DWE & Sommen, PCW 1999, On the indeterminacies of convolutive blind signal separation based on second-order statistics. in M Deriche, B Boashash & WW Boles (eds), Proc. ISSPA '99, Fifth International Symposium on Signal Processing and its Applications. Queensland University of Technology, Brisbane, QLD, Australia, pp. 215-218, ISSPA '99, Fifth International Symposium on Signal Processing and its Applications, Brisbane, Australia, 22/08/99.

On the indeterminacies of convolutive blind signal separation based on second-order statistics. / Schobben, D.W.E.; Sommen, P.C.W.
Proc. ISSPA '99, Fifth International Symposium on Signal Processing and its Applications. ed. / M. Deriche; B. Boashash; W.W. Boles. Brisbane, QLD, Australia: Queensland University of Technology, 1999. p. 215-218.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - On the indeterminacies of convolutive blind signal separation based on second-order statistics

AU - Schobben, D.W.E.

AU - Sommen, P.C.W.

PY - 1999

Y1 - 1999

N2 - Recently, several blind signal separation algorithms have been developed which are based on second order statistics. Little has been published however on whether second order statistics are sufficient to obtain a unique solution. Especially for applications that involve convolutive mixing and unmixing of signals that are correlated in time, there is a lack of knowledge on why and in what cases second order statistics suffice. This paper investigates the indeterminacies that are introduced when second order statistics are used and presents a theorem for the unmixing system to be uniquely found using second order statistics.

AB - Recently, several blind signal separation algorithms have been developed which are based on second order statistics. Little has been published however on whether second order statistics are sufficient to obtain a unique solution. Especially for applications that involve convolutive mixing and unmixing of signals that are correlated in time, there is a lack of knowledge on why and in what cases second order statistics suffice. This paper investigates the indeterminacies that are introduced when second order statistics are used and presents a theorem for the unmixing system to be uniquely found using second order statistics.

M3 - Conference contribution

SN - 1 86435 451 8

SP - 215

EP - 218

BT - Proc. ISSPA '99, Fifth International Symposium on Signal Processing and its Applications

A2 - Deriche, M.

A2 - Boashash, B.

A2 - Boles, W.W.

PB - Queensland University of Technology

CY - Brisbane, QLD, Australia

T2 - ISSPA '99, Fifth International Symposium on Signal Processing and its Applications

Y2 - 22 August 1999 through 25 August 1999

ER -

On the indeterminacies of convolutive blind signal separation based on second-order statistics

Abstract

Conference

Access to Document

Fingerprint

Cite this