An EM Algorithm for Audio Source Separation Based on the Convolutive Transfer Function

Xiaofei Li (1) , Laurent Girin (2, 1) , Radu Horaud (1)

1 PERCEPTION - Interpretation and Modelling of Images and Videos
2 GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing

This paper addresses the problem of audio source separation from (possibly under-determined) multichannel convolutive mixtures. We propose a separation method based on the convolutive transfer function (CTF) in the short-time Fourier transform domain. For strongly reverberant signals, the CTF is a much more appropriate model than the widely-used multiplicative transfer function approximation. An Expectation-Maximization (EM) algorithm is proposed to jointly estimate the model parameters, including the CTF coefficients of the mixing filters, and infer the sources. Experiments show that the proposed method provides very satisfactory performance on highly reverberant speech mixtures.

Keywords: Audio source separation; convolutive transfer function; EM algorithm

Domains: Machine Learning [cs.LG]; Sound [cs.SD]

Xiaofei Li, Laurent Girin, Radu Horaud. An EM Algorithm for Audio Source Separation Based on the Convolutive Transfer Function. WASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, NY, United States. pp.56-60, ⟨10.1109/WASPAA.2017.8169994⟩. ⟨hal-01568818⟩