Identification of Nonminimum Phase Systems Using Higher Order Statistics

Georgios B. Giannakis, Jerry M. Mendel

Research output: Contribution to journalArticlepeer-review

365 Scopus citations


In this paper we present a method for identification of linear, time-invariant, nonminimum phase systems when only output data are available. The input sequence need not be independent, but it must be non-Gaussian, with some special properties described in the text. We generally model a finite-dimensional system as an ARMA rational function of known orders, but the special cases of AR, MA, and all-pass models are also considered. To estimate the parameters of our model, we exploit both second- and higher order statistics of the output, which may be contaminated by additive, zero-mean, Gaussian white noise of unknown variance. The parameter estimators obtained are proved, under mild conditions, to be consistent. Simulations verify the performance of our method in relatively low signal-to-noise ratios, and when there is a model order mismatch.

Original languageEnglish (US)
Pages (from-to)360-377
Number of pages18
JournalIEEE Transactions on Acoustics, Speech, and Signal Processing
Issue number3
StatePublished - Mar 1989
Externally publishedYes

Bibliographical note

Funding Information:
Manuscript received March 28, 1986; revised July 5, 1988. This work was performed when the firat author wa5 at the University of Southern California, Los Angeles, and supported by the National Science Foundation under Grant ECS-860253 1, and by NOSC under Contract N66001-85-D-0203.


Dive into the research topics of 'Identification of Nonminimum Phase Systems Using Higher Order Statistics'. Together they form a unique fingerprint.

Cite this