´Mirror model´ gives separation of convolutive mixing of PNL mixtures

The proof is given that the so called ´mirror model´ as demixing model is able to recover original sources after non-trivial mixing. The issue explored is the capability to separate sources, in a blind way, after the convolutive mixing of post nonlinear (PNL) mixtures. The strictness of that kind of mixture produces non-trivial problems in separating signals without any adequate assumption on recovering architecture.