DocumentCode
2321850
Title
Implementation of an acoustic echo canceller based on NLMS-neural networks structures by using the VHDL
Author
Rabaa, Abdellatif Ben ; Zitouni, Abdelkerim ; Abid, Mohamed ; Tourki, Rached
Author_Institution
Sci. Fac., Electron. & Micro-Electron. Lab., Monastir, Tunisia
Volume
3
fYear
1998
fDate
7-11 Jun 1998
Firstpage
1789
Abstract
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
Keywords
digital signal processing chips; echo suppression; hardware description languages; least mean squares methods; neural chips; pipeline processing; recurrent neural nets; telephone sets; transfer functions; Galileo; IEEE 1076 Hardware Description Language standard; NLMS algorithms; NLMS-neural networks structures; RTL/logic synthesis tool; VHDL; Xilinx family; acoustic echo canceller; acoustic path; gate level; hands-free environment; pipelined recurrent neural network; practical hardware implementation; room/speakerphone transfer function; very high-speed digital circuits design; Circuit synthesis; Digital circuits; Echo cancellers; Hardware design languages; Loudspeakers; Network synthesis; Neural network hardware; Neural networks; Recurrent neural networks; Transfer functions;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, 1998. ICC 98. Conference Record. 1998 IEEE International Conference on
Conference_Location
Atlanta, GA
Print_ISBN
0-7803-4788-9
Type
conf
DOI
10.1109/ICC.1998.683137
Filename
683137
Link To Document