Low complexity nonlinear adaptive filters for acoustic echo cancellation in GSM handset receivers

High-quality mobile services need to compensate for acoustic echoes that may affect modern cellular phone receivers. To this purpose, adaptive linear filters are generally used since their low complexity allows realtime implementations. However, they often have to identify an acoustic echo path that may contain significant nonlinearities. Therefore, in such cases, a nonlinear model is required. It is well known that Volterra filters are well suited for modeling a large class of nonlinear systems, but they often require too many computational resources for a real-time implementation. The purpose of this paper is twofold. First of all, we propose to use a simplified quadratic Volterra filter, derived taking into account the characteristics of the most important nonlinearities that affect cellular receivers. Second, an efficient adaptation algorithm is derived which extends the Affine Projection (AP) algorithm, proposed for linear filters, to quadratic Volterra filters. This adaptation algorithm offers better convergence and tracking capabilities with respect to the standard LMS and NLMS algorithms. The reduced complexity and the fast adaptation rate make the echo cancellers we are proposing attractive for real-time implementations.