This paper presents a novel method for improving the low frequency performance of a microphone array by use of a twin codebook consisting of critical band energy and LPC distribution of speech. A modified Wiener filter created using these codebooks eliminates residual noise at low frequencies, which may result from the limitation of the array size or the beamforming algorithm. The preliminary simulation tests have shown that the proposed system is effective, and may provide good performance for those microphone array systems which are installed on a computer in an office, or in a moving vehicle.

A novel speech separation structure which simulates the cocktail party effect using a modified iterative Wiener filter and a multi-layer perceptron neural network is presented. The neural network is used as a speaker recognition system to control the iterative Wiener filter. The neural network is a modified perceptron with a hidden layer using feature data extracted from LPC cepstral analysis. The proposed technique has been successfully used for speech separation when the interference is competing speech or broad band noise.

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.