Differentiable Piano Model for MIDI-to-Audio Performance Synthesis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Differentiable Piano Model for MIDI-to-Audio Performance Synthesis

Modèle Différentiable de Piano pour la Synthèse de Performances MIDI-vers-Audio

Lenny Renault
Rémi Mignot
  • Fonction : Auteur
  • PersonId : 884002
Axel Roebel

Résumé

Recent neural-based synthesis models have achieved impressive results for musical instrument sound generation. In particular, the Differentiable Digital Signal Processing (DDSP) framework enables the usage of spectral modeling analysis and synthesis techniques in fully differentiable architectures. Yet currently, it has only been used for modeling monophonic instruments. Leveraging the interpretability and modularity of this framework, the present work introduces a polyphonic differentiable model for piano sound synthesis, conditioned on Musical Instrument Digital Interface (MIDI) inputs. The model architecture is motivated by high-level acoustic modeling knowledge of the instrument which, in tandem with the sound structure priors inherent to the DDSP components, makes for a lightweight, interpretable and realistic sounding piano model. The proposed model has been evaluated in a listening test, demonstrating improved sound quality compared to a benchmark neural-based piano model, with significantly less parameters and even with reduced training data. The same listening test indicates that physical-modeling-based models still achieve better quality, but the differentiability of our lightened approach encourages its usage in other musical tasks dealing with polyphonic audio and symbolic data.
Fichier principal
Vignette du fichier
DifferentiablePiano_DAFx2022.pdf (829.6 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03779081 , version 1 (16-09-2022)

Identifiants

Citer

Lenny Renault, Rémi Mignot, Axel Roebel. Differentiable Piano Model for MIDI-to-Audio Performance Synthesis. 25th International Conference on Digital Audio Effects (DAFx20in22), Sep 2022, Vienna, Austria. ⟨10.5281/zenodo.7092602⟩. ⟨hal-03779081⟩
88 Consultations
158 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More