Drumroll Please: Modeling Multi-Scale Rhythmic Gestures with Flexible Grids. Issue 1 (17th November 2021)

• Record Type: Journal Article
• Authors: Gillick, Jon; Yang, Joshua; Cella, Carmine-Emanuele; Bamman, David
• Is Part Of: Transactions of the International Society for Music Information Retrieval. Volume 4:Issue 1(2021)
• Page Start: 156
• Page End: 166
• Publication Date: 2021-11-17
• Subjects: Music Representations -- Music Generation -- Computational Creativity -- Machine Learning -- Music Production -- Human Computer Interaction; 025
• DOI: 10.5334/tismir.98
• Languages: English
• ISSNs: 2514-3298

Abstract

We present a new data representation for music modeling and generation called a Flexible Grid. This representation aims to balance flexibility with structure in order to encode all the musical events (notes or rhythmic onsets) in a dataset without quantizing or discarding any temporal information. In experiments with a dataset of MIDI drum performances, we find that when implemented in a Variational AutoEncoder (VAE) model, Flexible Grid representations can enable detailed generation of music performance data that includes multiple different gestures and articulations.