Pré-Publication, Document De Travail Année : 2025

Audio signal interpolation using optimal transportation of spectrograms

Résumé

We present a novel approach for generating an artificial audio signal that interpolates between given source and target sounds. Our approach relies on the computation of Wasserstein barycenters of the source and target spectrograms, followed by phase reconstruction and inversion. In contrast with previous works, our new method considers the spectrograms globally and does not operate on a temporal frame-to-frame basis. An other contribution is to endow the transportation cost matrix with a specific structure that prohibits remote displacements of energy along the time axis, and for which optimal transport is made possible by leveraging the unbalanced transport framework. The proposed cost matrix makes sense from the audio perspective and also allows to reduce the computation load. Results with synthetic musical notes and real environmental sounds illustrate the potential of our novel approach.
Fichier principal
Vignette du fichier
SSP2025-29.pdf (504) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04960810 , version 1 (21-02-2025)

Licence

Identifiants

  • HAL Id : hal-04960810 , version 1

Citer

David Valdivia, Marien Renaud, Elsa Cazelles, Cédric Févotte. Audio signal interpolation using optimal transportation of spectrograms. 2025. ⟨hal-04960810⟩
0 Consultations
0 Téléchargements

Partager

More