Notochord: a Flexible Probabilistic Model for Real-Time MIDI Performance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shepardson, Victor, Armitage, Jack, Magnusson, Thor
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910373088591872
author Shepardson, Victor
Armitage, Jack
Magnusson, Thor
author_facet Shepardson, Victor
Armitage, Jack
Magnusson, Thor
contents Deep learning-based probabilistic models of musical data are producing increasingly realistic results and promise to enter creative workflows of many kinds. Yet they have been little-studied in a performance setting, where the results of user actions typically ought to feel instantaneous. To enable such study, we designed Notochord, a deep probabilistic model for sequences of structured events, and trained an instance of it on the Lakh MIDI dataset. Our probabilistic formulation allows interpretable interventions at a sub-event level, which enables one model to act as a backbone for diverse interactive musical functions including steerable generation, harmonization, machine improvisation, and likelihood-based interfaces. Notochord can generate polyphonic and multi-track MIDI, and respond to inputs with latency below ten milliseconds. Training code, model checkpoints and interactive examples are provided as open source software.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12000
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Notochord: a Flexible Probabilistic Model for Real-Time MIDI Performance
Shepardson, Victor
Armitage, Jack
Magnusson, Thor
Sound
Artificial Intelligence
Audio and Speech Processing
Deep learning-based probabilistic models of musical data are producing increasingly realistic results and promise to enter creative workflows of many kinds. Yet they have been little-studied in a performance setting, where the results of user actions typically ought to feel instantaneous. To enable such study, we designed Notochord, a deep probabilistic model for sequences of structured events, and trained an instance of it on the Lakh MIDI dataset. Our probabilistic formulation allows interpretable interventions at a sub-event level, which enables one model to act as a backbone for diverse interactive musical functions including steerable generation, harmonization, machine improvisation, and likelihood-based interfaces. Notochord can generate polyphonic and multi-track MIDI, and respond to inputs with latency below ten milliseconds. Training code, model checkpoints and interactive examples are provided as open source software.
title Notochord: a Flexible Probabilistic Model for Real-Time MIDI Performance
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2403.12000