Common Fate Model for Unison source Separation

Abstract : In this paper we present a novel source separation method aiming to overcome the difficulty of modelling non-stationary signals. The method can be applied to mixtures of musical instruments with frequency and/or amplitude modulation, e.g. typically caused by vi-brato. It is based on a signal representation that divides the complex spectrogram into a grid of patches of arbitrary size. These complex patches are then processed by a two-dimensional discrete Fourier transform, forming a tensor representation which reveals spectral and temporal modulation textures. Our representation can be seen as an alternative to modulation transforms computed on magnitude spectrograms. An adapted factorization model allows to decompose different time-varying harmonic sources based on their particular common modulation profile: hence the name Common Fate Model. The method is evaluated on musical instrument mixtures playing the same fundamental frequency (unison), showing improvement over other state-of-the-art methods.
Type de document :
Communication dans un congrès
41st International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, Shanghai, China. IEEE, 2016, Proceedings of the 41st International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01248012
Contributeur : Roland Badeau <>
Soumis le : mercredi 27 janvier 2016 - 09:54:59
Dernière modification le : mercredi 20 février 2019 - 14:41:16
Document(s) archivé(s) le : jeudi 28 avril 2016 - 11:18:05

Fichier

common_fate_icassp2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01248012, version 1

Citation

Fabian-Robert Stöter, Antoine Liutkus, Roland Badeau, Bernd Edler, Paul Magron. Common Fate Model for Unison source Separation. 41st International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, Shanghai, China. IEEE, 2016, Proceedings of the 41st International Conference on Acoustics, Speech and Signal Processing (ICASSP). 〈hal-01248012〉

Partager

Métriques

Consultations de la notice

840

Téléchargements de fichiers

737