RECURSIVE LAlTICE FILTERS - A BRIEF OVEBVIEW
E. Satorius, H. J. Shensa · 1980
Becently lattice filters structures have been ep ployed in numerous adaptive filtering applications such as noise cancelling; speech processing; and data equalization. In thie paper we will be concerned with the algorithms that have been proposed to update the lattice filter coefficients. Zhese algoritb typically fall into one of tvo classes, those based on stochastic (gradient) formilations and those founded on a least squares criterion. The latter are =re complex; however, they provide for a faster response to sudden changes in is the purpose of this paper to provide a brief exthe input data (e.g., a rapid initial convergence). It position of the algoriths and to point out their various parallels. In particular, it is hoped that the simpler structure of the stochastic algorithms will shd some light on the =re complex least squares procedures.