A WEIGHTED GENERAL DISCRETE FOURIER TRANSFORM FOR THE FREQUENCY-DOMAIN BLIND SOURCE SEPARATION OF CONVOLUTIVE MIXTURES

This letter deals with the frequency domain Blind Source Separation of Convolutive Mixtures (CMBSS). From the frequency representation of the "overlap and save", a Weighted General Discrete Fourier Transform (WGDFT) is derived to replace the traditional Discrete Fourier Transform (DFT). The mixing matrix on each frequency bin could be estimated more precisely from WGDFT coefficients than from DFT coefficients, which improves separation performance. Simulation results verify the validity of WGDFT for frequency domain blind source separation of convolutive mixtures.

A TIME DOMAIN BLIND DECORRELATION METHOD OF CONVOLUTIVE MIXTURES BASED ON AN IIR MODEL

We study a time domain decorrelation method of source signal separation from convolutive sound mixtures based on an infinite impulse response （IIR） model. The IIR model uses fewer parameters to capture the physical mixing process and is useful for finding low dimensional separating solutions. We present inversion formulas to decorrelate the mixture signals and derive filter equations involving second order time lagged statistics of mixtures. We then formulate an 11 constrained minimization problem and solve it by an iterative method. Numerical experiments on recorded sound mixtures show that our method is capable of sound separation in low dimensional parameter spaces with good perceptual quality and low correlation coefficient comparable to the known infomax method.

Maximum Likelihood Blind Separation of Convolutively Mixed Discrete Sources

In this paper,a Maximum Likelihood(ML) approach,implemented by Expectation-Maximization(EM) algorithm,is proposed to blind separation of convolutively mixed discrete sources.In order to carry out the expectation procedure of the EM algorithm with a less computational load,the algorithm named Iterative Maximum Likelihood algorithm(IML) is proposed to calculate the likelihood and recover the source signals.An important feature of the ML approach is that it has robust performance in noise environments by treating the covariance matrix of the additive Gaussian noise as a parameter.Another striking feature of the ML approach is that it is possible to separate more sources than sensors by exploiting the finite alphabet property of the sources.Simulation results show that the proposed ML approach works well either in determined mixtures or underdetermined mixtures.Furthermore,the performance of the proposed ML algorithm is close to the performance with perfect knowledge of the channel filters.

A novel blind deconvolution algorithm using single frequency bin

Former frequency-domain blind devolution algorithms need to consider a large number of frequency bins and recover the sources in different orders and with different amplitudes in each frequency bin,so they suffer from permutation and amplitude indeterminacy troubles. Based on sliding discrete Fourier transform,the presented deconvolution algorithm can directly recover time-domain sources from frequency-domain convolutive model using single frequency bin. It only needs to execute blind sepa-ration of instantaneous mixture once there are no permutation and amplitude indeterminacy troubles. Compared with former algorithms,the algorithm greatly reduces the computation cost as only one frequency bin is considered. Its good and robust per-formance is demonstrated by simulations when the signal-to-noise-ratio is high.

Wideband Beamforming for Multipath Signals Based on Frequency Invariant Transformation

It is well known that the performance of conventional adaptive beamformers degrades severely due to the presence of coherent or correlated interferences(multipath propagation) and various techniques have been developed to improve the performance of the beamformer.However,most of the work in the past has been focused on the narrowband case.In this paper,the wideband beamforming problem in the presence of multipath signals is addressed,with a novel approach proposed by employing a pre-processing stage based on the frequency invariant beamforming(FIB) technique.In this approach,the received wideband array signals are first processed by an FIB network,and then a traditional narrowband adaptive beamformer or an appropriate instantaneous blind source separation(BSS) algorithm can be applied to the network outputs.It is shown that with the proposed structure,cancellation of the desired signal is reduced,leading to a significantly improved output signal to interference plus noise ratio(SINR).