Multichannel speech separation by eigendecomposition and its application to co-talker interference removal

This paper describes the concept of eigendecomposition for multichannel signal separation, an alternative method of enhancing the desired signal corrupted by interference. The method uses two observations that come from a pair of sensors, both of which contain the desired signal and the undesired signal(s). The method assumes that the desired signal and the undesired signal(s) are uncorrelated, and the signal-to-noise ratios (SNR´s) of each observation are different and not necessarily greater than unity. The technique has been successfully used to separate speech signals corrupted heavily by ambient noise, co-talker interference, and other sources such as background music. The method can also be applied to instances where more than two sensors are used by first forming two beams and then processing the output of the two beamformers