ADAPTIVE BLIND SOURCE SEPARATION IN ORDER SPECIFIED BY STOCHASTIC PROPERTIES

In adaptive blind source separation, the order of recov-ered source signals is unpredictable due to order inde-terminacy. However, it is sometimes desired that the reconstructed source signals be arranged in specified order according to their stochastic properties. To this end, some unsymmetry is introduced to the equilib-rium point, and a new unsymmetrical natural gradient algorithm is proposed, which can separate the source signals in desired order. The validity of the proposed al-gorithm is confirmed through extensive computer sim-ulations. 1