An Amplitude Spectral Capon Estimator with a Variable Filter Length

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

1 Citation (Scopus)
310 Downloads (Pure)

Resumé

The filter bank methods have been a popular non-parametric way of computing the complex amplitude spectrum. So far, the length of the filters in these filter banks has been set to some constant value independently of the data. In this paper, we take the first step towards considering the filter length as an unknown parameter. Specifically, we derive a very simple and approximate way of determining the optimal filter length in a data-adaptive way. Based on this analysis, we also derive a model averaged version of the forward and the forward-backward amplitude spectral Capon estimators. Through simulations, we show that these estimators significantly improve the estimation accuracy compared to the traditional Capon estimators.
OriginalsprogEngelsk
TidsskriftEuropean Signal Processing Conference (EUSIPCO)
Sider (fra-til)430-434
Antal sider5
ISSN2076-1465
StatusUdgivet - aug. 2012
Begivenhed20th European Signal Processing Conference - Bucharest, Rumænien
Varighed: 27 aug. 201231 aug. 2012

Konference

Konference20th European Signal Processing Conference
LandRumænien
ByBucharest
Periode27/08/201231/08/2012

Fingerprint

Filter banks

Citer dette

@inproceedings{1710188e74f8498d8c403f887c6c0c5d,
title = "An Amplitude Spectral Capon Estimator with a Variable Filter Length",
abstract = "The filter bank methods have been a popular non-parametric way of computing the complex amplitude spectrum. So far, the length of the filters in these filter banks has been set to some constant value independently of the data. In this paper, we take the first step towards considering the filter length as an unknown parameter. Specifically, we derive a very simple and approximate way of determining the optimal filter length in a data-adaptive way. Based on this analysis, we also derive a model averaged version of the forward and the forward-backward amplitude spectral Capon estimators. Through simulations, we show that these estimators significantly improve the estimation accuracy compared to the traditional Capon estimators.",
author = "Nielsen, {Jesper Kj{\ae}r} and Paris Smaragdis and Christensen, {Mads Gr{\ae}sb{\o}ll} and Jensen, {S{\o}ren Holdt}",
year = "2012",
month = "8",
language = "English",
pages = "430--434",
journal = "Proceedings of the European Signal Processing Conference",
issn = "2076-1465",
publisher = "European Association for Signal Processing (EURASIP)",

}

An Amplitude Spectral Capon Estimator with a Variable Filter Length. / Nielsen, Jesper Kjær; Smaragdis, Paris; Christensen, Mads Græsbøll; Jensen, Søren Holdt.

I: European Signal Processing Conference (EUSIPCO), 08.2012, s. 430-434.

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

TY - GEN

T1 - An Amplitude Spectral Capon Estimator with a Variable Filter Length

AU - Nielsen, Jesper Kjær

AU - Smaragdis, Paris

AU - Christensen, Mads Græsbøll

AU - Jensen, Søren Holdt

PY - 2012/8

Y1 - 2012/8

N2 - The filter bank methods have been a popular non-parametric way of computing the complex amplitude spectrum. So far, the length of the filters in these filter banks has been set to some constant value independently of the data. In this paper, we take the first step towards considering the filter length as an unknown parameter. Specifically, we derive a very simple and approximate way of determining the optimal filter length in a data-adaptive way. Based on this analysis, we also derive a model averaged version of the forward and the forward-backward amplitude spectral Capon estimators. Through simulations, we show that these estimators significantly improve the estimation accuracy compared to the traditional Capon estimators.

AB - The filter bank methods have been a popular non-parametric way of computing the complex amplitude spectrum. So far, the length of the filters in these filter banks has been set to some constant value independently of the data. In this paper, we take the first step towards considering the filter length as an unknown parameter. Specifically, we derive a very simple and approximate way of determining the optimal filter length in a data-adaptive way. Based on this analysis, we also derive a model averaged version of the forward and the forward-backward amplitude spectral Capon estimators. Through simulations, we show that these estimators significantly improve the estimation accuracy compared to the traditional Capon estimators.

UR - http://www.scopus.com/inward/record.url?scp=84869761703&partnerID=8YFLogxK

M3 - Conference article in Journal

SP - 430

EP - 434

JO - Proceedings of the European Signal Processing Conference

JF - Proceedings of the European Signal Processing Conference

SN - 2076-1465

ER -