M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Poćwiardowski, Jakub, Modrzejewski, Mateusz, Tatara, Marek S.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915517844946944
author Poćwiardowski, Jakub
Modrzejewski, Mateusz
Tatara, Marek S.
author_facet Poćwiardowski, Jakub
Modrzejewski, Mateusz
Tatara, Marek S.
contents This work introduces the M6(GPT)3 composer system, capable of generating complete, multi-minute musical compositions with complex structures in any time signature, in the MIDI domain from input descriptions in natural language. The system utilizes an autoregressive transformer language model to map natural language prompts to composition parameters in JSON format. The defined structure includes time signature, scales, chord progressions, and valence-arousal values, from which accompaniment, melody, bass, motif, and percussion tracks are created. We propose a genetic algorithm for the generation of melodic elements. The algorithm incorporates mutations with musical significance and a fitness function based on normal distribution and predefined musical feature values. The values adaptively evolve, influenced by emotional parameters and distinct playing styles. The system for generating percussion in any time signature utilises probabilistic methods, including Markov chains. Through both human and objective evaluations, we demonstrate that our music generation approach outperforms baselines on specific, musically meaningful metrics, offering a viable alternative to purely neural network-based systems.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12638
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
Poćwiardowski, Jakub
Modrzejewski, Mateusz
Tatara, Marek S.
Sound
Human-Computer Interaction
Audio and Speech Processing
H.5.5; I.2.7; I.2.8; G.3
This work introduces the M6(GPT)3 composer system, capable of generating complete, multi-minute musical compositions with complex structures in any time signature, in the MIDI domain from input descriptions in natural language. The system utilizes an autoregressive transformer language model to map natural language prompts to composition parameters in JSON format. The defined structure includes time signature, scales, chord progressions, and valence-arousal values, from which accompaniment, melody, bass, motif, and percussion tracks are created. We propose a genetic algorithm for the generation of melodic elements. The algorithm incorporates mutations with musical significance and a fitness function based on normal distribution and predefined musical feature values. The values adaptively evolve, influenced by emotional parameters and distinct playing styles. The system for generating percussion in any time signature utilises probabilistic methods, including Markov chains. Through both human and objective evaluations, we demonstrate that our music generation approach outperforms baselines on specific, musically meaningful metrics, offering a viable alternative to purely neural network-based systems.
title M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
topic Sound
Human-Computer Interaction
Audio and Speech Processing
H.5.5; I.2.7; I.2.8; G.3
url https://arxiv.org/abs/2409.12638