A recursive adaptive lattice filters for impulsive signals

The existence of impulsive noise with alpha-stable distributions has been addressed in many applications. Some adaptive lattice algorithms that fractional lower order moments of residual errors are used to updated the filter coefficients are presented. In this paper, a new recursive adaptive lattice algorithm is proposed for adaptive filtering of alpha-stable AR processes. The performance of this algorithm is compared to that of those stochastic gradient-based algorithms. It is shown that the proposed algorithm achieves a superior convergence speed with respect to the other algorithms.