Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ou, Longshen, Zhao, Jingwei, Wang, Ziyu, Xia, Gus, Liang, Qihao, Wang, Torin Hopkins Ye
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908628547534848
author Ou, Longshen
Zhao, Jingwei
Wang, Ziyu
Xia, Gus
Liang, Qihao
Wang, Torin Hopkins Ye
author_facet Ou, Longshen
Zhao, Jingwei
Wang, Ziyu
Xia, Gus
Liang, Qihao
Wang, Torin Hopkins Ye
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
Ou, Longshen
Zhao, Jingwei
Wang, Ziyu
Xia, Gus
Liang, Qihao
Wang, Torin Hopkins Ye
Sound
Computation and Language
Audio and Speech Processing
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.
title Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2408.15176