Expressive Piano Performance Rendering from Unpaired Data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Expressive Piano Performance Rendering from Unpaired Data

Résumé

Recent advances in data-driven expressive performance rendering have enabled automatic models to reproduce the characteristics and the variability of human performances of musical compositions. However, these models need to be trained with aligned pairs of scores and performances and they rely notably on score-specific markings, which limits their scope of application. This work tackles the piano performance rendering task in a low-informed setting by only considering the score note information and without aligned data. The proposed model relies on an adversarial training where the basic score notes properties are modified in order to reproduce the expressive qualities contained in a dataset of real performances. First results for unaligned score-to-performance rendering are presented through a conducted listening test. While the interpretation quality is not on par with highly-supervised methods and human renditions, our method shows promising results for transferring realistic expressivity into scores.
Fichier principal
Vignette du fichier
Perf_Render_DAFx23_LBR.pdf (546.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04221612 , version 1 (28-09-2023)

Licence

Paternité

Identifiants

Citer

Lenny Renault, Rémi Mignot, Axel Roebel. Expressive Piano Performance Rendering from Unpaired Data. International Conference on Digital Audio Effects (DAFx23), Sep 2023, Copenhague, Denmark. pp.355--358, ⟨10.5281/zenodo.8386761⟩. ⟨hal-04221612⟩
71 Consultations
60 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More