SEPARATION OF A MIXTURE OF INDEPENDENT SIGNALS USING TIME-DELAYED CORRELATIONS

The problem of separating n linearly superimposed uncorrelated signals and determining their mixing coefficients is reduced to an eigenvalue problem which involves the simultaneous diagonalization of two symmet ric matrices whose elements are measurable time delayed correlation fu nctions. The diagonalization matrix can be determined from a cost func tion whose number of minima is equal the number of degenerate solution s. Our approach offers the possibility to separate also nonlinear mixt ures of signals.