Blind separation of post-nonlinear mixtures using gaussianizing transformations and temporal decorrelation

At the previous workshop (ICA2001) we proposed the ACETD method that reduces the post-nonlinear blind source separation problem (PNL BSS) to a linear BSS problem [18]. The method utilizes the Alternating Conditional Expectation (ACE) algorithm to approximately invert the (post-)nonlinear functions. In this contribution, we propose an alternative procedure called Gaussianizing transformation, which is motivated by the fact that linearly mixed signals before nonlinear transformation are approximately Gaussian distributed. This heuristic, but simple and efficient procedure yields similar results as the ACE method and can thus be used as a fast and effective equalization method. After equalizing the nonlinearities, temporal decorrelation separation (TDSEP) allows us to recover the source signals. Numerical simulations on realistic examples are performed to compare “Gauss-TD” with “ACE-TD”.