A hybrid LMS-LMF scheme for echo cancellation

The coe cients of an echo canceller with a nearend section and a far-end section are usually updated with the same updating scheme, such as the LMS algorithm. In this paper we propose a novel scheme for echo cancellation that is based on the minimization of two di erent cost functions, i.e., one for the near-end section and a di erent one for the far-end section. Two approaches are addressed and only one of them lead to a substantial improvement in performance over the LMS algorithm when it is applied to both sections of the echo canceller. The proposed scheme is also shown to be robust to noise variations, which is not the case for the LMS algorithm.