Stable learning algorithm for low-distortion blind separation of real speech mixture combining multistage ICA and linear prediction

We propose a stable algorithm for blind source separation (BSS) combining multistage ICA (MSICA) and linear prediction. The MSICA in which frequency-domain ICA (FDICA) for a rough separation is followed by time-domain ICA (TDICA) to remove residual crosstalk. For temporally correlated signals, we must use TDICA with a nonholonomic constraint to avoid the decorrelation effect from the holonomic constraint. However, the stability cannot be guaranteed in the nonholonomic case. To solve the problem, the linear predictors estimated from the roughly separated signals by FDICA are inserted before the holonomic TDICA as a prewhitening processing, and the dewhitening is performed after TDICA. The stability of the proposed algorithm can be guaranteed by the holonomic constraint, and the pre/dewhitening processing prevents the decorrelation.