LooperGP: A Loopable Sequence Model for Live Coding Performance using GuitarPro Tablature

TL;DR

LooperGP is a novel sequence model that enables live coding performances by generating musically meaningful, loopable guitar tablature phrases with controllable structure, trained on a large dataset of musical loops.

Contribution

It introduces a method to steer a Transformer-XL model to produce structured, loopable musical phrases suitable for live coding, addressing control and form issues in symbolic music generation.

Findings

Generated 3x more loopable phrases than baseline.

Achieved positive median ratings in originality, coherence, and smoothness.

Demonstrated potential as a live coding performance tool.

Abstract

Despite their impressive offline results, deep learning models for symbolic music generation are not widely used in live performances due to a deficit of musically meaningful control parameters and a lack of structured musical form in their outputs. To address these issues we introduce LooperGP, a method for steering a Transformer-XL model towards generating loopable musical phrases of a specified number of bars and time signature, enabling a tool for live coding performances. We show that by training LooperGP on a dataset of 93,681 musical loops extracted from the DadaGP dataset, we are able to steer its generative output towards generating 3x as many loopable phrases as our baseline. In a subjective listening test conducted by 31 participants, LooperGP loops achieved positive median ratings in originality, musical coherence and loop smoothness, demonstrating its potential as a performance tool.