An Affine Combination of TVLMS Adaptive Filters for Echo Cancellation

This paper deals with the statistical behaviour of an affine combination of the outputs of two TVLMS adaptive filters that simultaneously adapting the same white Gaussian inputs and it’s cancelling the echoes by system identification. The purpose of the combination is to obtain TVLMS adaptive filters with faster convergence and small steady-state mean-square deviation (MSD). The linear combination is used in this paper, is a generalization of the convex combination, in which the combination factor ) (n  is restricted to interval (0, 1). The viewpoint is taken that each of the two Filters produces dependent estimates of the unknown channel. Thus, there exists a sequence of optimal affine combining coefficients which minimizes the MSE and it find’s the unknown system response. These results will be verified on the MAT LAB 7.8.0 version software by using signal processing tool box. The applications of this paper are System Identification with low MSE and Echo Cancellation. Now a day in real time applications can be implemented using an affine combination of TVLMS adaptive filters because, it is easy way to design, implementation, robustness, with low MSE, and high level noise cancellation and it requires less number of computational operations. Keywords—Adaptive filters, affine combination, analysis, time varying least mean square (TVLMS), stochastic algorithms.