Separation of a mixture of independent signals using time delayed correlations.

The problem of separating n linearly superimposed uncorrelated signals and determing their mixing coeecents is reduced to an Eigenvalue problem which involves the simultaneous diagonalisation of two symmetric matrices whose elements are measureable time delayed correlation functions. The diagonali-sation matrix can be determined from a cost function whose number of minima is equal the number of degenerate solutions. Our approach ooers the possibility to separate also nonlinear mixtures of signals.