Majorization-minimization algorithm for smooth Itakura-Saito nonnegative matrix factorization

Nonnegative matrix factorization (NMF) with the Itakura-Saito divergence has proven efficient for audio source separation and music transcription, where the signal power spectrogram is factored into a "dictionary" matrix times an "activation" matrix. Given the nature of audio sig...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) s. 1980 - 1983
Hlavní autor: Fevotte, Cedric
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2011
Témata:
audio signal representation
Itakura-Saito divergence
Kernel
Markov processes
Minimization
Nonnegative matrix factorization (NMF)
Optimization
Polynomials
regularization by smoothness
Signal processing algorithms
single-channel source separation
Spectrogram
ISBN:9781457705380, 1457705389
ISSN:1520-6149
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Nonnegative matrix factorization (NMF) with the Itakura-Saito divergence has proven efficient for audio source separation and music transcription, where the signal power spectrogram is factored into a "dictionary" matrix times an "activation" matrix. Given the nature of audio signals it is expected that the activation coefficients exhibit smoothness along time frames. This may be enforced by penalizing the NMF objective function with an extra term reflecting smoothness of the activation coefficients. We propose a novel regularization term that solves some deficiencies of our previous work and leads to an efficient implementation using a majorization-minimization procedure.
ISBN:9781457705380
1457705389
ISSN:1520-6149
DOI:10.1109/ICASSP.2011.5946898