Microphone array speech enhancement by Bayesian estimation of spectral amplitude and phase

Microphone arrays provide new opportunities for noise reduction and speech enhancement. This paper presents a novel decomposition of the estimation problems for short-time spectral amplitude (STSA), log STSA, and phase in the Bayesian estimation framework. The decomposition is based on the notion of sufficient statistics for the microphone array case. It nicely generalizes the wellknown single-channel Ephraim-Malah estimators (1984, 1985) to the microphone array case. We also compare noise reduction obtained in the single channel with the two- and four-channel cases on real data.