Efficient realisation of adaptive filter using an orthogonal projection method

Author

Sommen, P.C.W. ; van Valburg, C.J.

Author_Institution

Philips Res. Lab., Eindhoven, Netherlands

fYear

1989

Firstpage

940

Abstract

An orthogonal projection (OP) algorithm with some decorrelation properties is described. In two dimensions this OP algorithm makes a projection on a plane, rather then on a line as in the LMS (least mean squares) algorithm. The authors show that this algorithm can be changed in such a way that it can perfectly decorrelate an AR (autoregressive) input signal. In this algorithm (OPAR), an orthogonal projection on a line is made in such a way that the update is orthogonal to all its past updates. The authors introduce an efficient realization of this algorithm, the EOPAR algorithm, having LMS complexity. Simulation results are given for the different algorithms

Keywords

adaptive filters; digital filters; filtering and prediction theory; EOPAR algorithm; adaptive filter; autoregressive; decorrelation properties; digital filters; least mean squares; orthogonal projection method; Adaptive filters; Convergence; Decorrelation; Digital filters; Digital signal processing; Echo cancellers; Least squares approximation; Noise cancellation; Signal processing algorithms; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on

Conference_Location

Glasgow

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1989.266584

Filename

266584