Maximum-Likelihood Autoregressive Estimation on Incomplete Spectra

Author

Weruaga, Luis ; Kepesi, M.

Author_Institution

VISKOM, Austrian Acad. of Sci., Vienna, Austria

Volume

3

fYear

2007

fDate

15-20 April 2007

Abstract

Frequency-selective autoregressive (AR) estimation is arousing increasing interest. We propose herein a new method to estimate the AR model from a reduced set of spectral samples. The proposed method is founded on the maximum likelihood criterion over the logarithmic spectral residue, and it is implemented efficiently with a multivariate Newton-Raphson algorithm. Results over deterministic and stochastic scenarios show its excellent performance.

Keywords

Newton-Raphson method; autoregressive processes; maximum likelihood estimation; signal sampling; spectral analysis; frequency-selective autoregressive estimation; incomplete spectra; logarithmic spectral residue; maximum-likelihood autoregressive estimation; multivariate Newton-Raphson algorithm; spectral samples; Autocorrelation; Fourier transforms; Frequency domain analysis; Frequency estimation; Maximum likelihood estimation; Minimization methods; Predictive models; Spectral analysis; Stochastic processes; Transfer functions; Autoregressive model; frequency domain; incomplete spectrum; maximum likelihood;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Type

conf

DOI

10.1109/ICASSP.2007.366851

Filename

4217881