Title :
Spectral sensitivity and convergence rate in adaptive IIR filtering
Author :
Rodriguez-Fonollosa, José A. ; Masgrau, Enrique
Author_Institution :
Dept. de Teoria del Senyal i Comunicacions, Univ. Politecnica de Catalunya, Barcelona, Spain
Abstract :
An algorithm for adaptive IIR lattice filtering in which the log-area ratio parameters are updated instead of the reflection coefficients is derived. This modification gives an error surface with no instability region and more uniform behavior. The results show that the application of the Gauss-Newton method to the log-area ratio parameters effectively gives an algorithm with a convergence rate faster than that of any other IIR adaptive algorithm
Keywords :
adaptive filters; convergence; filtering and prediction theory; sensitivity; Gauss-Newton method; adaptive IIR filtering; convergence rate; error surface; lattice filtering; log-area ratio parameters; parameter updating; Adaptive algorithm; Adaptive filters; Convergence; Filtering algorithms; IIR filters; Lattices; Least squares methods; Newton method; Recursive estimation; Reflection;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112098
