Multichannel speech enhancement using Bayesian spectral amplitude estimation

This paper introduces two short-time spectral amplitude estimators for speech enhancement with multiple microphones. Based on joint Gaussian models of speech and noise Fourier coefficients the clean speech amplitudes are estimated with respect to the MMSE or the MAP criterion. The estimators outperform single microphone minimum mean square amplitude estimators when the speech is highly correlated and the noise is sufficiently uncorrelated. Whereas the first MMSE estimator also requires the desired signals to be in phase, the second MAP estimator performs a direction-independent noise reduction. The estimators are generalizations of the well known single channel MMSE estimator derived by Ephraim and Malah (1984) and the MAP estimator derived by Wolfe and Godsill see (Proceedings of the 11th IEEE Workshop on Statistical Signal Processing, p.496-499, August 2001) respectively.