The information you asked about the separation algorithm [1] are following:

[1] Jiri Malek, Zbynek Koldovsky and Petr Tichavsky, Adaptive Time-Domain Blind Separation of Speech Signals, submitted to LVA/ICA 2010, 2010

Jiri Malek (1), Zbynek Koldovsky (1) and Petr Tichavsky (2)

(1)
Faculty of Mechatronic and Interdisciplinary Studies
Technical University of Liberec, Studentska 2, 461 17 Liberec,
Czech Republic
{jiri . malek, zbynek . koldovsky} (at) tul . cz

(2)
Institute of Information Theory and Automation,
Pod vodarenskou vezi 4,
P.O.Box 18, 182 08 Praha 8, Czech Republic
tichavsk (at) utia . cas . cz

In [1], an adaptive algorithm for blind audio source separation
(BASS) of moving sources via Independent Component Analysis
(ICA) in time-domain is described.

The algorithm performed the separation with its internal parameters set to
L=30
aplha=4
P=6144
T=512
beta2=0.95

Average running time per test in task 1:	5.63s
Total running time of task 1 per GHz of CPU:	177.8s

Average running time per test in task 2:	702s
Total running time of task 2 per GHz of CPU:	792s