Integrating Text-to-Music Models with Language Models: Composing Long Structured Music Pieces
Sound
2024-10-08 v3 Machine Learning
Audio and Speech Processing
Abstract
Recent music generation methods based on transformers have a context window of up to a minute. The music generated by these methods is largely unstructured beyond the context window. With a longer context window, learning long-scale structures from musical data is a prohibitively challenging problem. This paper proposes integrating a text-to-music model with a large language model to generate music with form. The papers discusses the solutions to the challenges of such integration. The experimental results show that the proposed method can generate 2.5-minute-long music that is highly structured, strongly organized, and cohesive.
Cite
@article{arxiv.2410.00344,
title = {Integrating Text-to-Music Models with Language Models: Composing Long Structured Music Pieces},
author = {Lilac Atassi},
journal= {arXiv preprint arXiv:2410.00344},
year = {2024}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2404.11976