A fast RLS transversal filter for adaptive linear phase filtering

Abstract

AbstractA fast transversal filter algorithm is presented for the adaptive recursive least‐squares design of filters with linear phase. Connections with a popular method of spectrum estimation are explored. The algorithm is derived in a new framework, for the prewindowed given data case. Exact and soft‐constraint initialization are discussed and an improved rescue procedure is proposed. Data sequence weighting is introduced to allow for arbitrarily time‐varying weighting strategies, facilitating the tracking of arbitrarily non‐stationary phenomena.