Title :
Higher-order spectrum estimation via noncausal autoregressive modeling and deconvolution
Author :
Nikias, Chrysostomos L. ; Chiang, Hsing-Hsing
Author_Institution :
Commun. & Digital Signal Process. Center, Northeastern Univ., Boston, MA, USA
fDate :
12/1/1988 12:00:00 AM
Abstract :
A method for nonminimum-phase finite impulse response (FIR) system identification is introduced that is based on noncausal autoregressive (AR) modeling of the third moments of the output data. The magnitude and phase response of the FIR system are expressed in terms of the parameters of a noncausal AR model. The set of AR parameters is obtained by solving an overdetermined linear system of equations that is formed using third-moment estimates of the output data. The performance of the method is illustrated with simulation examples
Keywords :
identification; signal processing; spectral analysis; FIR; deconvolution; noncausal autoregressive modelling; nonminimum-phase finite impulse response; overdetermined linear system; spectrum estimation; system identification; third-moment estimates; Deconvolution; Digital signal processing; Estimation error; Finite impulse response filter; Frequency; Narrowband; Nonuniform sampling; Sampling methods; Signal processing; Spectral analysis;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
