Title :
Test results of a chip for the separation of mixed and filtered signals
Author :
Gharbi, Ammar B. ; Salam, Fathi M.
Author_Institution :
Circuits, Syst. & Artificial Neural Networks Lab., Michigan State Univ., East Lansing, MI, USA
fDate :
11/1/1995 12:00:00 AM
Abstract :
We describe an algorithm and chip implementation for separating a mixture of unknown, but independent, temporal signals in static and dynamic environments. The proposed algorithm, which is a simple but conceptually powerful modification of the Herault and Jutten (HJ) algorithm, proves to be robust to parameter variations. Moreover, we present some chip results to quantify the performance of the modified algorithm in static and dynamic (mixing and filtering) environments
Keywords :
CMOS analogue integrated circuits; analogue processing circuits; neural chips; signal processing; speech processing; CMOS implementation; Herault-Jutten algorithm; chip implementation; dynamic environments; filtered signals; mixed signals; neural network algorithm; neurochip; parameter variation robustness; separation of independent sources; signal separation; speech segment separation; static environments; temporal signals; Circuit testing; Filtering; Magnetic separation; Optical amplifiers; Optical filters; Optical mixing; Sensor arrays; Solid state circuits; Stimulated emission; Vectors;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
