Self-Supervised VQ-VAE for One-Shot Music Style Transfer - Equipe Signal, Statistique et Apprentissage Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Self-Supervised VQ-VAE for One-Shot Music Style Transfer

Résumé

Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its introduction. In contrast, related tasks in the music audio domain remained, until recently, largely untackled. While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms. On the other hand, the results of existing one-shot audio style transfer methods on musical inputs are not as compelling. In this work, we are specifically interested in the problem of one-shot timbre transfer. We present a novel method for this task, based on an extension of the vector-quantized variational autoencoder (VQ-VAE), along with a simple self-supervised learning strategy designed to obtain disentangled representations of timbre and pitch. We evaluate the method using a set of objective metrics and show that it is able to outperform selected baselines.
Fichier principal
Vignette du fichier
paper.pdf (261.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03132940 , version 1 (10-06-2021)

Identifiants

Citer

Ondřej Cífka, Alexey Ozerov, Umut Şimşekli, Gael Richard. Self-Supervised VQ-VAE for One-Shot Music Style Transfer. ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto / Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414235⟩. ⟨hal-03132940⟩
4251 Consultations
480 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More