Comparative Evaluation of ANN and LMS Based Algorithms for Adaptive Noise Cancellation

Abstract

The major hindrance to effective speech communication is the presence of surrounding noise and interference that tend to mask and corrupt the intelligent part of the signal. To remove the noisy components of the speech signals, adaptive noise cancellation (ANC) technique has been found efficient. In literature, several algorithms have been developed for filter coefficients adjustment for ANC systems, one of which is the least mean square (LMS). In this study, artificial neural network (ANN) based ANC technique has been proposed and compared with the conventional LMS. The algorithms were implemented and tested with a real time noisy speech signal. Simulation results are also presented to support the experimental and mathematics analysis. The performance analysis has been evaluated in terms of the means square error (MSE) of the algorithms. The developed ANN based algorithm gives a better MSE value compared to LMS when applied on speech signal.