|Personal pages of ZBYNĚK KOLDOVSKÝ|
Abstract: Here, we provide a Matlab GUI (in p-code) for the T-ABCD method for blind separation of convolutive mixture of audio sources. The algorithm works in time-domain and is based on a complete unconstrained decomposition of the observation space spanned by input signals. The observation space may be defined in a general way, which allows application of long separating filters, although its dimension is low. In this respect, the variant provided here utilizes Laguerre separating filters. The decomposition is done by an appropriate independent component analysis (ICA) algorithm giving independent components that are grouped into clusters corresponding to the original sources. Components of the clusters are combined by a reconstruction procedure after estimating microphone responses (images) of the original sources.
Matlab GUI package in p-code (July 20, 2011): here (P-code generated in Matlab 126.96.36.1999 (R2009b).) Now, a command-line code of T-ABCD for more flexible usage (e.g., testing/comparison purposes) is included. Please do not hesitate to contact us in case of any troubles with the codes.Corresponding papers:
A complete SiSEC 2010 dataset for testing and benchmarks (task "Robust blind linear/non-linear separation of short two-sources-two-microphones recordings"): here
Instalation and execution of the T-ABCD package: Unzip the package into a directory, run Matlab, load microphone
recordings into rows of a matrix x,
and type (in Matlab)
See the readme.txt file.