Performance analysis of the adjusted step size NLMS algorithm

Abstract

An adaptive noise canceller is a well-known method for removing noise from noise-corrupted speech. The problem arises in many situations such as airplane cockpits and automobiles. Tire adjusted step size NLMS (normalized least mean squares) algorithm incorporating a variable step size parameter whose values are based on the ratio of signal-to-noise power has very good convergence speed and low steady-state misadjustment. This paper extends the results of the adjusted step size NLMS algorithm [J. Kim et al., 2003] by investigating the adjusted step size NLMS algorithm approaches when large and abrupt changes of the desired signal as well as the noise signal are present. Simulation results are presented to compare the performance of the adjusted step size NLMS algorithm with the fixed step size LMS algorithm and other commonly used variable step size LMS algorithms.