HARMONIC RETRIEVAL USING HIGHER-ORDER STATISTICS - A DETERMINISTIC FORMULATION

Given a single record, we consider the problem of estimating the param eters of a harmonic signal buried in noise, The observed data are mode led as a sinusoidal signal plus additive Gaussian noise of unknown cov ariance. We define novel higher order statistics-referred to as ''mixe d'' cumulants-that can be consistently estimated using a single record and are insensitive to colored Gaussian noise. Employing fourth-order mixed cumulants, we estimate the sinusoid parameters using a consiste nt, nonlinear matching approach, The algorithm requires an initial est imate that we obtain from a consistent, linear estimator, Finally, we examine the performance of the proposed method via simulations.