Simplied gradient calculation in iir lattice adaptive filters
Rights accessOpen Access
A simplified algorithm is presented for computing the gradient in adaptive IIR (infinite impulse response) lattice filters. For a filter with N zeros and N poles, this algorithm requires only order N computations. Several computer simulations were performed to compare the performance of the proposed O(N) formulation and the conventional O(N/sup 2/) formulation, and no difference in their behavior was found. In these simulations the full Hessian and the diagonal Hessian adaptive algorithms were used in a system-identification configuration. It is concluded that the proposed method allows the development of robust adaptive IIR algorithms with a cost proportional to the filter order.
CitationFonollosa, José A. R., Masgrau, E. Simplied gradient calculation in iir lattice adaptive filters. "IEEE transactions on signal processing", Juliol 1991, vol. 39, núm. 7, p. 1702-1705.