Low-rank time-frequency synthesis




Date(s) : 30/06/2017   iCal
14 h 00 min - 15 h 00 min

Many single-channel signal decomposition techniques rely on a low-rank factorization of a time-frequency transform. In particular, nonnegative matrix factorization (NMF) of the spectrogram – the (power) magnitude of the short-time Fourier transform (STFT) – has been considered in many audio applications. In this setting, NMF with the Itakura-Saito divergence was shown to underly a generative Gaussian composite model (GCM) of the STFT, a step forward from more empirical approaches based on ad-hoc transform and divergence specifications. Still, the GCM is not yet a generative model of the raw signal itself, but only of its STFT. The work presented in this paper fills in this ultimate gap by proposing a novel signal synthesis model with low-rank time-frequency structure. In particular, our new approach opens doors to multi-resolution representations, that were not possible in the traditional NMF setting. We describe expectation-maximization algorithms for estimation in the new model and report audio signal processing results with music decomposition and new approach to the compressive sampling inverse problem, that exploits latent low-rank time-frequency structure instead of sparsity, with superior results for the considered data.

http://webpages.lss.supelec.fr/perso/matthieu.kowalski/

Catégories Pas de Catégories



Retour en haut 

Secured By miniOrange