A robust adaptive filtering algorithm with variable step size

The authors present a variable-step adaptive filtering algorithm (VS-NLMS) that is robust in the presence of interference. An estimated cross-correlation coefficient between the input reference signal and the error signal is used as the variable step size. Compared with the conventional fixed-step adaptive filtering algorithm (NLMS), the VS-NLMS algorithm can achieve much lower misadjustment noise in the steady state with the same convergence speed and tracking ability. The advantageous properties of the VS-NLMS algorithm are confirmed by computer simulation.<
>