Communication Dans Un Congrès Année : 2024

Audio Conditioning for Music Generation via Discrete Bottleneck Features

Simon Rouard
  • Fonction : Auteur
  • PersonId : 1501867
Jade Copet
  • Fonction : Auteur
Alexandre Défossez
  • Fonction : Auteur

Résumé

While most music generation models use textual or parametric conditioning (e.g. tempo, harmony, musical genre), we propose to condition a language model based music generation system with audio input. Our exploration involves two distinct strategies. The first strategy, termed textual inversion, leverages a pre-trained text-to-music model to map audio input to corresponding "pseudowords" in the textual embedding space. For the second model we train a music language model from scratch jointly with a text conditioner and a quantized audio feature extractor. At inference time, we can mix textual and audio conditioning and balance them thanks to a novel double classifier free guidance method. We conduct automatic and human studies that validates our approach. We will release the code and we provide music samples on https://musicgenstyle.github.io in order to show the quality of our model.
Fichier principal
Vignette du fichier
2407.12563v2.pdf (522) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04928259 , version 1 (04-02-2025)

Identifiants

Citer

Simon Rouard, Yossi Adi, Jade Copet, Axel Roebel, Alexandre Défossez. Audio Conditioning for Music Generation via Discrete Bottleneck Features. ISMIR 2024, Nov 2024, San Francisco California, United States. ⟨hal-04928259⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More