This paper derives two spatio–temporal extensions of the well-known FastICA algorithm of Hyvärinen and Oja that are applicable to the convolutive blind source separation task. Our time–domain algorithms combine multichannel spatio–temporal prewhitening via multistage least-squares linear prediction with novel adaptive procedures that impose paraunitary constraints on the multichannel separation...

Nowadays, most oilfields have entered the high water cut stage of waterflood development. The importance oil–water separation technology becomes more obvious. Gravity is one commonly used treatment techniques for produced fluid. gravitational separator has a large processing capacity and wide application range, but its structure relatively simple efficiency gradually falls behind to meet curren...

We propose a novel algorithm for the separation of convolutive speech mixtures using two-microphone recordings, based on the combination of independent component analysis (ICA) and ideal binary mask (IBM), together with a post-filtering process in the cepstral domain. The proposed algorithm consists of three steps. First, a constrained convolutive ICA algorithm is applied to separate the source...

In order to find a measure of the dynamical features of phase separation kinetics during spinodal decomposition of a liquid binary mixture (like water and cyclohexane , water and 2,6 lutidiene or methanol and cyclohexane), we study both the initial fast exponential-like growth (the Cahn-Hilliard regime) and the subsequent cross-over to a much slower, non-exponential long time growth (the so-cal...

Blind source separation for convolutive mixture of speech signals has been addressed in many literatures. However, widely applied Multichannel Blind Deconvolution (MBD) method suffers whitening effect or arbitrary filtering problem which results in dramatic decrease of Automatic Speech Recognition system’s performance. In present paper, a new MBD based multistage method is proposed, in which co...

The performance of existing blind speech separation methods is limited in a realistic reverberant environment, where a need for long un-mixing filters is imperative. We first show how these methods suffer while trying to balance the competing objectives of frequency-domain permutation alignment and spectral resolution. We then propose a multistage multiresolution algorithm, which aligns the un-...