Steer-by-prior Editing of Symbolic Music Loops

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jonason, Nicolas, Casini, Luca, Sturm, Bob L. T.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909279841157120
author Jonason, Nicolas
Casini, Luca
Sturm, Bob L. T.
author_facet Jonason, Nicolas
Casini, Luca
Sturm, Bob L. T.
contents With the goal of building a system capable of controllable symbolic music loop generation and editing, this paper explores a generalisation of Masked Language Modelling we call Superposed Language Modelling. Rather than input tokens being known or unknown, a Superposed Language Model takes priors over the sequence as input, enabling us to apply various constraints to the generation at inference time. After detailing our approach, we demonstrate our model across various editing tasks in the domain of multi-instrument MIDI loops. We end by highlighting some limitations of the approach and avenues for future work. We provides examples from the SLM across multiple generation and editing tasks at https://erl-j.github.io/slm-mml-demo/.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02434
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Steer-by-prior Editing of Symbolic Music Loops
Jonason, Nicolas
Casini, Luca
Sturm, Bob L. T.
Sound
Audio and Speech Processing
With the goal of building a system capable of controllable symbolic music loop generation and editing, this paper explores a generalisation of Masked Language Modelling we call Superposed Language Modelling. Rather than input tokens being known or unknown, a Superposed Language Model takes priors over the sequence as input, enabling us to apply various constraints to the generation at inference time. After detailing our approach, we demonstrate our model across various editing tasks in the domain of multi-instrument MIDI loops. We end by highlighting some limitations of the approach and avenues for future work. We provides examples from the SLM across multiple generation and editing tasks at https://erl-j.github.io/slm-mml-demo/.
title Steer-by-prior Editing of Symbolic Music Loops
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2408.02434