TY - GEN
T1 - Multichannel HR-NMF for modelling convolutive mixtures of non-stationary signals in the time-frequency domain
AU - Badeau, Roland
AU - Plumbley, Mark D.
PY - 2013/12/1
Y1 - 2013/12/1
N2 - 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 NMF (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 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.
AB - 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 NMF (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 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.
KW - Multichannel signal analysis
KW - Non-stationary signal modelling
KW - Separation of convolutive mixtures
KW - Time-frequency analysis
KW - Variational EM algorithm
U2 - 10.1109/WASPAA.2013.6701824
DO - 10.1109/WASPAA.2013.6701824
M3 - Conference contribution
AN - SCOPUS:84893553889
SN - 9781479909728
T3 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
BT - 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2013
T2 - 2013 14th IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2013
Y2 - 20 October 2013 through 23 October 2013
ER -