Time-domain distributed multichannel Wiener filtering speech enhancement algorithm

To recover pure speech from observed speech, this paper presents a time-domain multi-channel Wiener filter speech enhancement algorithm for the distributed speech model. For reducing the noise from noisy speech in time domain, this paper first gives the formula about the energy of noise reduction and speech distortion, then establishes the optimization problem on noise reduction and speech distortion, and finally solves the optimization problem to get the formula of the optimal linear filter. In addition, this paper uses an iterative method to estimate the source speech signal autocorrelation matrix, which improves the estimation accuracy. Simulation experiment results show the proposed algorithm can obtain the better performance than several classical multi-channel speech enhancement algorithms.