Conference · NeurIPS 2025
Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
Advances in Neural Information Processing Systems (NeurIPS), San Diego, CA, USA, 2025.
Abstract
We present a unified framework for automatic multitrack music arrangement that enables a single pre-trained symbolic music model to handle diverse arrangement scenarios, including reinterpretation, simplification, and additive generation. At its core is a segment-level reconstruction objective operating on token-level disentangled content and style, allowing for flexible any-to-any instrumentation transformations at inference time. To support track-wise modeling, we introduce REMI-z, a structured tokenization scheme for multitrack symbolic music that enhances modeling efficiency and effectiveness for both arrangement tasks and unconditional generation. Our method outperforms task-specific state-of-the-art models on representative tasks in different arrangement scenarios—band arrangement, piano reduction, and drum arrangement, in both objective metrics and perceptual evaluations. Taken together, our framework demonstrates strong generality and suggests broader applicability in symbolic music-to-music transformation.
Cite
Longshen Ou, Jingwei Zhao, Ziyu Wang, Gus Xia, Qihao Liang, Torin Hopkins, Ye Wang. 2025. Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization. Advances in Neural Information Processing Systems (NeurIPS).
@inproceedings{ou2025unifying,
title = {{Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization}},
author = {Ou, Longshen and Zhao, Jingwei and Wang, Ziyu and Xia, Gus and Liang, Qihao and Hopkins, Torin and Wang, Ye},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
year = {2025}
}