Single-Channel Speech Separation Using Soft Mask Filtering

Abstract

We present an approach for separating two speech signals when only one single recording of their linear mixture is available. For this purpose, we derive a filter, which we call the soft mask filter, using minimum mean square error (MMSE) estimation of the log spectral vectors of sources given the mixture's log spectral vectors. The soft mask filter's parameters are estimated using the mean and variance of the underlying sources which are modeled using the Gaussian composite source modeling (CSM) approach. It is also shown that the binary mask filter which has been empirically and extensively used in single-channel speech separation techniques is, in fact, a simplified form of the soft mask filter. The soft mask filtering technique is compared with the binary mask and Wiener filtering approaches when the input consists of male+male, female+female, and male+female mixtures. The experimental results in terms of signal-to-noise ratio (SNR) and segmental SNR show that soft mask filtering outperforms binary mask and Wiener filtering.