Multi-Source Musaicing Using Non-Negative Matrix Factor 2-D Deconvolution - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Multi-Source Musaicing Using Non-Negative Matrix Factor 2-D Deconvolution

Résumé

A recent trend is to use Music Information Retrieval algorithms for creativity. When considering the audio signal as observation, a well-known method of data-driven synthesis is the " concatenative synthesis " also named musaicing (audio mosaicing) [7]. We propose here to extend the mu-saicing framework by including recent advances in audio source separation. We propose a method which allows reproducing a target music track by superimposing in time and frequency constitutive elements obtained using source separation methods. 1
Fichier principal
Vignette du fichier
Foroughmand2017.pdf (375.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01709680 , version 1 (15-02-2018)

Identifiants

  • HAL Id : hal-01709680 , version 1

Citer

Hadrien Foroughmand, Geoffroy Peeters. Multi-Source Musaicing Using Non-Negative Matrix Factor 2-D Deconvolution. 18th International Society for Music Information Retrieval Late-Breaking Demo Session, Oct 2017, Suzhou, China. ⟨hal-01709680⟩
112 Consultations
75 Téléchargements

Partager

Gmail Facebook X LinkedIn More