Expectation-Maximization for Speech Source Separation Using Convolutive Transfer Function
This addresses speech source separation for audio processing applications, but it is incremental as it builds on existing EM methods with a more accurate model.
The paper tackled the problem of under-determined speech source separation from multichannel microphone signals by proposing a convolutive transfer function model to represent room filters more accurately than the narrowband assumption, and experiments showed it provides very satisfactory performance in highly reverberant environments.
This paper addresses the problem of under-determinded speech source separation from multichannel microphone singals, i.e. the convolutive mixtures of multiple sources. The time-domain signals are first transformed to the short-time Fourier transform (STFT) domain. To represent the room filters in the STFT domain, instead of the widely-used narrowband assumption, we propose to use a more accurate model, i.e. the convolutive transfer function (CTF). At each frequency band, the CTF coefficients of the mixing filters and the STFT coefficients of the sources are jointly estimated by maximizing the likelihood of the microphone signals, which is resolved by an Expectation-Maximization (EM) algorithm. Experiments show that the proposed method provides very satisfactory performance under highly reverberant environments.