Spectral Sensitivity and Convergence Rate in Adaptive

It is known that, in the autoregressive model the spectral sensitivity curves are almost flat for the log-area ratios and in this paper it is shown that this property can be useful in adaptive IIR filtering. A new IIR lattice-form algorithm for adaptive filtering is proposed in which the update equation is applied to these parameters instead of the reflection coefficients. This transformation gives a more uniform performance surface with no unstability region and, as a result, the behavior of the Gauss Newton search method is clearly improved.