Implementation of blind source separation of speech signals using independent component analysis

Blind source separation (BSS) is the separation of sources without having prior information about the mixtures. This is a major problem in real time world whether we have to identify a particular person in the crowd or it be an area of biomedical signal extraction like Electroencephalogram (EEG). It is really very difficult to estimate a source out of the mixtures. If the brain is malfunctioning, just by looking at the EEG we can’t say which part of brain is causing malfunction because the outputs are the mixtures from 21 electrodes. Similarly in a multiple speaker environment, when numbers of people are speaking simultaneously it is difficult to identify a particular speaker. Hence there is a need of source separation. Several methods are available for separating the sources like independent component analysis (ICA), auto decorrelation filtering (ADF) and beamforming. Here ICA has been used for the purposes of separation of signals and Matlab –GUI has been implemented for creating the user friendly environment.