Acoustic Echo Cancellation using Adaptive Algorithms

This paper presents the comparison between different adaptive algorithms usages in acoustic echo cancellation. This comparison includes the cancellation of echo generated in room using different adaptive algorithms Least Mean Square (LMS), Normalized Least Mean Square (NLMS), Improved Proportionate Normalized Least Mean Square (IPNLMS) and Recursive Least Squares (RLS) Algorithms. The goal of this work is to choose an optimal algorithm for cancelling acoustic echo noise from the speech signal. There are many adaptive algorithms available in the literature for echo cancellation and every algorithm has its own properties. Our aim is to achieve higher ERLE (amount of echo cancelled) in dB at a higher rate of convergence with low complexity and achieve good amount of SNR (signal to noise ratio). The results verified by using subjective analysis.