TY - GEN
T1 - Scale-invariant probabilistic latent component analysis
AU - Hennequin, Romain
AU - Badeau, Roland
AU - David, Bertrand
PY - 2011/12/19
Y1 - 2011/12/19
N2 - In this paper, we present a new method for decomposing musical spectrograms. This method is similar to shift-invariant Probabilistic Latent Component Analysis, but, when the latter works with constant Q spectrograms (i.e. with a logarithmic frequency resolution), our technique is designed to decompose standard short time Fourier transform spectrograms (i.e. with a linear frequency resolution). This makes it possible to easily reconstruct the latent signals (which can be useful for source separation).
AB - In this paper, we present a new method for decomposing musical spectrograms. This method is similar to shift-invariant Probabilistic Latent Component Analysis, but, when the latter works with constant Q spectrograms (i.e. with a logarithmic frequency resolution), our technique is designed to decompose standard short time Fourier transform spectrograms (i.e. with a linear frequency resolution). This makes it possible to easily reconstruct the latent signals (which can be useful for source separation).
KW - Music signal processing
KW - non-negative matrix factorization
KW - probabilistic latent component analysis
KW - shiftinvariant decomposition
U2 - 10.1109/ASPAA.2011.6082265
DO - 10.1109/ASPAA.2011.6082265
M3 - Conference contribution
AN - SCOPUS:83455170766
SN - 9781457706912
T3 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
SP - 129
EP - 132
BT - 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2011
T2 - 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2011
Y2 - 16 October 2011 through 19 October 2011
ER -