Share Email Print

Proceedings Paper

Spectral generating theorem for nonstationary stochastic signals
Author(s): James W. Pitton
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper addresses time-frequency (TF) analysis from a statistical signal processing perspective, with the goal of developing a general statistical methodology for TF analysis. We review earlier work on statistical models for nonstationary stochastic signals, including frequency modulated locally stationary processes, which have covariance functions which yield nonnegative Wigner distributions. For such processes, time- frequency spectra may be defined without invoking 'local-' or 'quasi-' stationarity. These results are extended to include general time-varying linear systems and their associated time- frequency spectra. Any time-varying linear system driven by white noise has associated with it a nonnegative time-frequency spectrum. The bilinear class of time-frequency distributions are estimators of this time-frequency spectrum, as are adaptive methods such as positive time-frequency distributions and adaptive multitaper spectrograms. An analysis of the statistical properties of these estimators, including moments and distributional properties, is reviewed.

Paper Details

Date Published: 13 November 2000
PDF: 8 pages
Proc. SPIE 4116, Advanced Signal Processing Algorithms, Architectures, and Implementations X, (13 November 2000); doi: 10.1117/12.406521
Show Author Affiliations
James W. Pitton, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 4116:
Advanced Signal Processing Algorithms, Architectures, and Implementations X
Franklin T. Luk, Editor(s)

© SPIE. Terms of Use
Back to Top