Implementation of an acoustic echo canceller based on NLMS-neural networks structures by using the VHDL

Abstract

In this paper, a cascaded Pipelined Recurrent Neural NetworMNLMS structure is employed in an attempt to model the roomfspeakerphone transfer function and acoustic path in a hands-gee environment. To investigate the feasibility of practical hardware implementation of the proposed structure, this paper aims at implementing the Pipelined Recurrent Neural Network and NLMS algorithms by using the VHDL. VHBL is the name of the IEEE 1076 Hardware Description Language standard for very high-speed digital circuits design. Galileo, an RTLAogic synthesis tool, has been used in order to generate the gate level of the proposed structure. The Xilinx family is chosen as target technology.