Unlocking Potential in Pre-Trained Music Language Models for Versatile Multi-Track Music Arrangement

作     者：Ou, Longshen Zhao, Jingwei Wang, Ziyu Xia, Gus Wang, Ye 

作者机构：Sound and Music Computing Lab School of Computing NUS Singapore Institute of Data Science NUS Singapore Integrative Sciences and Engineering Programme NUS Graduate School Singapore Music X Lab MBZUAI NYU Shanghai China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Computer music 

摘      要：Large language models have shown significant capabilities across various domains, including symbolic music generation. However, leveraging these pre-trained models for controllable music arrangement tasks, each requiring different forms of musical information as control, remains a novel challenge. In this paper, we propose a unified sequence-to-sequence framework that enables the fine-tuning of a symbolic music language model for multiple multi-track arrangement tasks, including band arrangement, piano reduction, drum arrangement, and voice separation. Our experiments demonstrate that the proposed approach consistently achieves higher musical quality compared to task-specific baselines across all four tasks. Furthermore, through additional experiments on probing analysis, we show the pre-training phase equips the model with essential knowledge to understand musical conditions, which is hard to acquired solely through task-specific fine-tuning.1 Copyright © 2024, The Authors. All rights reserved.