Communication Dans Un Congrès Année : 2020

Adaptive Drum Machine Microtiming with Transfer Learning and RNNs

Résumé

We introduce rolypoly˜, the first drum machine for live performance that adapts its microtiming in relation to a human musician. We leverage state-of-the-art work in expressive performance modelling with recurrent nets, towards real-time application on the micro scale. Our models are pretrained on the Groove MIDI Dataset from Magenta, and then fine-tuned iteratively over several duet performances of a new piece. We propose a method for defining training targets based on previous performances, rather than a prior ground truth. The agent is able to adapt to human timing nuances, and can achieve effects such as morphing a rhythm from straight to swing.

Fichier principal
Vignette du fichier
ISMIR2020-LBD-422-abstract.pdf (173.47 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04096259 , version 1 (12-05-2023)

Licence

Identifiants

  • HAL Id : hal-04096259 , version 1

Citer

Grigore Burloiu. Adaptive Drum Machine Microtiming with Transfer Learning and RNNs. Extended Abstracts for the Late-Breaking Demo Session of the 21st Int. Society for Music Information Retrieval Conf., Oct 2020, Montreal (ONLINE), Canada. ⟨hal-04096259⟩
61 Consultations
151 Téléchargements

Partager

  • More