Shifted Independent Component Analysis

Morten Mørup; Kristoffer Hougaard Madsen; Lars Kai Hansen

Shifted Independent Component Analysis

Morten Mørup, Kristoffer Hougaard Madsen, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

1160 Downloads (Orbit)

Abstract

Delayed mixing is a problem of theoretical interest and practical importance, e.g., in speech processing, bio-medical signal analysis and financial data modelling. Most previous analyses have been based on models with integer shifts, i.e., shifts by a number of samples, and have often been carried out using time-domain representation. Here, we explore the fact that a shift t in the time domain corresponds to a multiplication of exp(-iwt) in the frequency domain. Using this property an algorithm in the case of sources

Original language	English
Title of host publication	7th International Conference on Independent Component Analysis and Signal Separation : ICA2007
Publication date	2007
Pages	89-96
Publication status	Published - 2007
Event	7^th International Conference on Independent component analysis and signal separation - London, United Kingdom Duration: 9 Sept 2007 → 12 Sept 2007 Conference number: 7

Conference

Conference	7^th International Conference on Independent component analysis and signal separation
Number	7
Country/Territory	United Kingdom
City	London
Period	09/09/2007 → 12/09/2007

Keywords

Shifted Independent Component Analysis (SICA)

Access to Document

SICASubmitted manuscript, 224 KB

OpenUrl availability

Full text

Cite this

@inproceedings{27cf76a0bc73486ea39c7abf45f66195,

title = "Shifted Independent Component Analysis",

abstract = "Delayed mixing is a problem of theoretical interest and practical importance, e.g., in speech processing, bio-medical signal analysis and financial data modelling. Most previous analyses have been based on models with integer shifts, i.e., shifts by a number of samples, and have often been carried out using time-domain representation. Here, we explore the fact that a shift t in the time domain corresponds to a multiplication of exp(-iwt) in the frequency domain. Using this property an algorithm in the case of sources",

keywords = "Shifted Independent Component Analysis (SICA)",

author = "Morten M{\o}rup and Madsen, {Kristoffer Hougaard} and Hansen, {Lars Kai}",

year = "2007",

language = "English",

pages = "89--96",

booktitle = "7th International Conference on Independent Component Analysis and Signal Separation",

note = "7<sup>th</sup> International Conference on Independent component analysis and signal separation, ICA07 ; Conference date: 09-09-2007 Through 12-09-2007",

}

TY - GEN

T1 - Shifted Independent Component Analysis

AU - Mørup, Morten

AU - Madsen, Kristoffer Hougaard

AU - Hansen, Lars Kai

N1 - Conference code: 7

PY - 2007

Y1 - 2007

N2 - Delayed mixing is a problem of theoretical interest and practical importance, e.g., in speech processing, bio-medical signal analysis and financial data modelling. Most previous analyses have been based on models with integer shifts, i.e., shifts by a number of samples, and have often been carried out using time-domain representation. Here, we explore the fact that a shift t in the time domain corresponds to a multiplication of exp(-iwt) in the frequency domain. Using this property an algorithm in the case of sources

AB - Delayed mixing is a problem of theoretical interest and practical importance, e.g., in speech processing, bio-medical signal analysis and financial data modelling. Most previous analyses have been based on models with integer shifts, i.e., shifts by a number of samples, and have often been carried out using time-domain representation. Here, we explore the fact that a shift t in the time domain corresponds to a multiplication of exp(-iwt) in the frequency domain. Using this property an algorithm in the case of sources

KW - Shifted Independent Component Analysis (SICA)

M3 - Article in proceedings

SP - 89

EP - 96

BT - 7th International Conference on Independent Component Analysis and Signal Separation

T2 - 7<sup>th</sup> International Conference on Independent component analysis and signal separation

Y2 - 9 September 2007 through 12 September 2007

ER -