On matching correlation sequences by parametric spectral models

The correlation matching property of all-pole models does not extend readily to pole-zero models. It is proved that, if the number of poles in a pole-zero model is strictly less than the number of given correlations, a pole-zero model that matches the given correlations may not exist, irrespective o...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on signal processing 1991-01, Vol.39 (1), p.214-216
Main Authors: Makhoul, J., Steinhardt, A.O.
Format: Article
Language:English
Subjects:
Autocorrelation
Cepstral analysis
Entropy
Parameter estimation
Poles and zeros
Signal processing algorithms
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The correlation matching property of all-pole models does not extend readily to pole-zero models. It is proved that, if the number of poles in a pole-zero model is strictly less than the number of given correlations, a pole-zero model that matches the given correlations may not exist, irrespective of the number of zeros in the model. It is also shown that if one adds a set of cepstral constraints, a maximum-entropy pole-zero model that matches the correlation and cepstral constraints may not exist. It is concluded that pole-zero modeling minimizing some error criterion might be preferable to exact constraint matching.< >
ISSN:1053-587X
1941-0476
DOI:10.1109/78.80787