VS-SC: A Variable Step Size NLMS Algorithm

In this paper we introduce VS-SC, an efficient variable step size normalized LMS algorithm for updating the coefficients of a FIR structure in noise and echo canceling applications. In the VS-SC algorithm the step size adjustment is controlled by the square of the correlation between the output error and the adaptive filter output. The proposed algorithm is compared with the conventional normalized LMS algorithm and another variable step algorithm. Simulation results, using white noise, confirm that better convergence rates can be achieved with the proposed scheme.