Implementation of blind source separation for multi-input

Abstract

The present work shows, implementation of neural ICA algorithms with multiple inputs using VHDL Design in a Field Programmable Gate Array (FPGA). We designed an architecture modular using INFOMAX algorithm in order to add n inputs for audio signals. Some simulations results using VHDL are presented using music and voice recorded. The study of performance is made in a net 2times2 and also a net of 3times3.

7 Figures and Tables

Showing 1-9 of 9 references

Computing Science and Automatic Control (CCE 2008) IEEE Catalog Number: CFP08827-CDR ISBN: 978-1-4244-2499-3 Library of Congress

  • 2008

Implementación de la red neuronal H-J para la identificación de fuentes independientes

  • M A Aleman, L N C A Oliva, Lopez
  • 2007
1 Excerpt

Source separation without prior Knowledge: the maximum likelihood solution

  • M Gaeta, J Lacoume
  • 1990
1 Excerpt