New adaptive IIR filtering algorithms based on the Steiglitz-McBride method

Abstract

This correspondence introduces a family of algorithms based on the Steiglitz-McBride (SM) method for adaptive IIR filtering. The main feature of the proposed algorithms is to remove the parameter bias induced by colored measurement noise. The conceptual similarities between the SM method and the equation error method are explored in order to analyze some properties of the new algorithms. The main analysis results concern the consistency of the parameter estimates and local convergence. A set of simulations in a system identification configuration is included in order to verify the improved performance of the new algorithms based on the SM method.