Multichannel HR-NMF for modelling convolutive mixtures of non-stationary signals in the time-frequency domain

Roland Badeau, Mark D. Plumbley
2013 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics  
In the literature, several probabilistic models involving latent components have been proposed for modelling time-frequency (TF) representations of audio signals (such as spectrograms), notably in the nonnegative matrix factorization (NMF) literature. Among them, the recent high resolution (HR)-NMF model is able to take both phases and local correlations in each frequency band into account, and its potential has been illustrated in applications such as source separation and audio inpainting. In
more » ... this paper, HR-NMF is extended to multichannel signals and to convolutive mixtures. A fast variational expectation-maximization (EM) algorithm is proposed to estimate the enhanced model. This algorithm is applied to a stereophonic piano signal, and proves capable of accurately modelling reverberation and restoring missing observations. Index Terms-Non-stationary signal modelling, Timefrequency analysis, Separation of convolutive mixtures, Multichannel signal analysis, Variational EM algorithm.
doi:10.1109/waspaa.2013.6701824 dblp:conf/waspaa/BadeauP13 fatcat:dgtv7mkxmzdqrbsmfyxq6t6jza