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

A cascaded pipelined recurrent neural network/NLMS structure is employed in an attempt to model the room/speakerphone transfer function and acoustic path in a hands-free 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 VHDL. VHDL is the name of the IEEE 1076 Hardware Description Language standard for very high-speed digital circuits design. Galileo, an RTL/logic synthesis tool, has been used in order to generate the gate level of the proposed structure. The Xilinx family is chosen as target technology.