Content-based Controls For Music Large Language Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Liwei, Xia, Gus, Jiang, Junyan, Zhang, Yixiao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912061395566592
author Lin, Liwei
Xia, Gus
Jiang, Junyan
Zhang, Yixiao
author_facet Lin, Liwei
Xia, Gus
Jiang, Junyan
Zhang, Yixiao
contents Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions. However, the control power of text controls on music is intrinsically limited, as they can only describe music indirectly through meta-data (such as singers and instruments) or high-level representations (such as genre and emotion). We aim to further equip the models with direct and content-based controls on innate music languages such as pitch, chords and drum track. To this end, we contribute Coco-Mulla, a content-based control method for music large language modeling. It uses a parameter-efficient fine-tuning (PEFT) method tailored for Transformer-based audio models. Experiments show that our approach achieved high-quality music generation with low-resource semi-supervised learning, tuning with less than 4% parameters compared to the original model and training on a small dataset with fewer than 300 songs. Moreover, our approach enables effective content-based controls, and we illustrate the control power via chords and rhythms, two of the most salient features of music audio. Furthermore, we show that by combining content-based controls and text descriptions, our system achieves flexible music variation generation and arrangement. Our source codes and demos are available online.
format Preprint
id arxiv_https___arxiv_org_abs_2310_17162
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Content-based Controls For Music Large Language Modeling
Lin, Liwei
Xia, Gus
Jiang, Junyan
Zhang, Yixiao
Artificial Intelligence
Sound
Audio and Speech Processing
Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions. However, the control power of text controls on music is intrinsically limited, as they can only describe music indirectly through meta-data (such as singers and instruments) or high-level representations (such as genre and emotion). We aim to further equip the models with direct and content-based controls on innate music languages such as pitch, chords and drum track. To this end, we contribute Coco-Mulla, a content-based control method for music large language modeling. It uses a parameter-efficient fine-tuning (PEFT) method tailored for Transformer-based audio models. Experiments show that our approach achieved high-quality music generation with low-resource semi-supervised learning, tuning with less than 4% parameters compared to the original model and training on a small dataset with fewer than 300 songs. Moreover, our approach enables effective content-based controls, and we illustrate the control power via chords and rhythms, two of the most salient features of music audio. Furthermore, we show that by combining content-based controls and text descriptions, our system achieves flexible music variation generation and arrangement. Our source codes and demos are available online.
title Content-based Controls For Music Large Language Modeling
topic Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2310.17162