Informed source separation via compressive graph signal sampling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Informed source separation via compressive graph signal sampling

Résumé

We propose a novel informed source separation method for audio object coding based on a recent sampling theory for smooth signals on graphs. Assuming that only one source is active at each time-frequency point, we compute an ideal map indicating which source is active at each time-frequency point at the encoder. This map is then sampled with a compressive graph signal sampling strategy that guarantees accurate and stable recovery at the decoder. The graph is built using feature vectors, computed using non-negative matrix factorization, that allows us to connect similar source activations in the time-frequency plane. We show that the proposed approach performs better than state-of-the-art methods at low bitrate.
Fichier principal
Vignette du fichier
Puy_et_al_ICASSP_2017.pdf (719.22 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01447982 , version 1 (27-01-2017)

Identifiants

  • HAL Id : hal-01447982 , version 1

Citer

Gilles Puy, Alexey Ozerov, Ngoc Q K Duong, Patrick Pérez. Informed source separation via compressive graph signal sampling. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), Mar 2017, New Orleans, United States. ⟨hal-01447982⟩
104 Consultations
431 Téléchargements

Partager

Gmail Facebook X LinkedIn More