Generalization of maximum entropy spectrum extension method

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Given (n + 1) consecutive autocorrelations of a stationary discrete-time stochastic process, one interesting question is how to extend this finite sequence so that the power spectral density associated with the resulting infinite sequence of correlations is nonnegative everywhere. It is well known that when the Hermitian Toeplitz matrix generated from the given correlations is positive-definite the problem has an infinite number of solutions and the particular solution that maximizes entropy results in a stable all-pole model of order n. Since maximization of entropy is equivalent to maximization of the minimum mean square error associated with one-step predictors, the problem of obtaining admissible extensions that maximize the minimum mean square error associated with k-step (k ≤ n) predictors, which are compatible with the given correlations, is studied. It is shown that the resulting spectrum corresponds to that of a stable ARMA (n, k-1) process. The details of this particular extension method are worked out for a two-step predictor.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherPubl by IEEE
Pages2619-2622
Number of pages4
Volume5
StatePublished - 1990
Event1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5) - Albuquerque, New Mexico, USA
Duration: Apr 3 1990Apr 6 1990

Other

Other1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5)
CityAlbuquerque, New Mexico, USA
Period4/3/904/6/90

Fingerprint

Mean square error
Entropy
entropy
Power spectral density
predictions
Random processes
Autocorrelation
autoregressive moving average
Poles
stochastic processes
autocorrelation
poles
matrices

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Pillai, U. (1990). Generalization of maximum entropy spectrum extension method. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 5, pp. 2619-2622). Publ by IEEE.

Generalization of maximum entropy spectrum extension method. / Pillai, Unnikrishna.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 5 Publ by IEEE, 1990. p. 2619-2622.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pillai, U 1990, Generalization of maximum entropy spectrum extension method. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 5, Publ by IEEE, pp. 2619-2622, 1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5), Albuquerque, New Mexico, USA, 4/3/90.
Pillai U. Generalization of maximum entropy spectrum extension method. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 5. Publ by IEEE. 1990. p. 2619-2622
Pillai, Unnikrishna. / Generalization of maximum entropy spectrum extension method. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 5 Publ by IEEE, 1990. pp. 2619-2622
@inproceedings{2c105ba25bcc4554bf90e9a88de49323,
title = "Generalization of maximum entropy spectrum extension method",
abstract = "Given (n + 1) consecutive autocorrelations of a stationary discrete-time stochastic process, one interesting question is how to extend this finite sequence so that the power spectral density associated with the resulting infinite sequence of correlations is nonnegative everywhere. It is well known that when the Hermitian Toeplitz matrix generated from the given correlations is positive-definite the problem has an infinite number of solutions and the particular solution that maximizes entropy results in a stable all-pole model of order n. Since maximization of entropy is equivalent to maximization of the minimum mean square error associated with one-step predictors, the problem of obtaining admissible extensions that maximize the minimum mean square error associated with k-step (k ≤ n) predictors, which are compatible with the given correlations, is studied. It is shown that the resulting spectrum corresponds to that of a stable ARMA (n, k-1) process. The details of this particular extension method are worked out for a two-step predictor.",
author = "Unnikrishna Pillai",
year = "1990",
language = "English (US)",
volume = "5",
pages = "2619--2622",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Generalization of maximum entropy spectrum extension method

AU - Pillai, Unnikrishna

PY - 1990

Y1 - 1990

N2 - Given (n + 1) consecutive autocorrelations of a stationary discrete-time stochastic process, one interesting question is how to extend this finite sequence so that the power spectral density associated with the resulting infinite sequence of correlations is nonnegative everywhere. It is well known that when the Hermitian Toeplitz matrix generated from the given correlations is positive-definite the problem has an infinite number of solutions and the particular solution that maximizes entropy results in a stable all-pole model of order n. Since maximization of entropy is equivalent to maximization of the minimum mean square error associated with one-step predictors, the problem of obtaining admissible extensions that maximize the minimum mean square error associated with k-step (k ≤ n) predictors, which are compatible with the given correlations, is studied. It is shown that the resulting spectrum corresponds to that of a stable ARMA (n, k-1) process. The details of this particular extension method are worked out for a two-step predictor.

AB - Given (n + 1) consecutive autocorrelations of a stationary discrete-time stochastic process, one interesting question is how to extend this finite sequence so that the power spectral density associated with the resulting infinite sequence of correlations is nonnegative everywhere. It is well known that when the Hermitian Toeplitz matrix generated from the given correlations is positive-definite the problem has an infinite number of solutions and the particular solution that maximizes entropy results in a stable all-pole model of order n. Since maximization of entropy is equivalent to maximization of the minimum mean square error associated with one-step predictors, the problem of obtaining admissible extensions that maximize the minimum mean square error associated with k-step (k ≤ n) predictors, which are compatible with the given correlations, is studied. It is shown that the resulting spectrum corresponds to that of a stable ARMA (n, k-1) process. The details of this particular extension method are worked out for a two-step predictor.

UR - http://www.scopus.com/inward/record.url?scp=0025593241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025593241&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025593241

VL - 5

SP - 2619

EP - 2622

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - Publ by IEEE

ER -