A Robust Nonlinear Microphone Array Postfilter For Noise Reduction

We propose a robust nonlinear microphone array postfilter for noise reduction. This postfilter is formulated as a function of noise power ratio before and after beamforming and a local speech-to-observation power ratio. The two ratios are readily obtained during beamforming, and can be approximated by local speech posterior probability or time-frequency masks of neural network. This avoids the difficulty in estimating local speech and noise variances of a beamformed signal. On the CHiME-3 test set, we have evaluated our proposed postfilter in comparison with two other postfiltering methods, and our proposed postfilter has produced the best objective scores on the simulated noisy speech as well as higher listening preference scores on real noisy speech.