MusicWeaver: Composer-Style Structural Editing and Minute-Scale Coherent Music Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xuanchen, Wang, Heng, Cai, Weidong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912856764579840
author Wang, Xuanchen
Wang, Heng
Cai, Weidong
author_facet Wang, Xuanchen
Wang, Heng
Cai, Weidong
contents Recent advances in music generation produce impressive samples, however, practical creation still lacks two key capabilities: composer-style structural editing and minute-scale coherence. We present MusicWeaver, a framework for generating and editing long-range music using a human-interpretable intermediate representation with guaranteed edit locality. MusicWeaver decomposes generation into two stages: it first predicts a structured plan, a multi-level song program encoding musical attributes that composers can directly edit, and then renders audio conditioned on this plan. To ensure minute-scale coherence, we introduce a Global-Local Diffusion Transformer, where a global path captures long-range musical progression via compressed representations and memory, while a local path synthesizes fine-grained acoustic detail. We further propose a Motif Memory Retrieval module that enables consistent motif recurrence with controllable variation. For editing, we propose Projected Diffusion Inpainting, an inpainting method that denoises only user-specified regions and preserves unchanged content, allowing repeated edits without drift. Finally, we introduce Structure Coherence Score and Edit Fidelity Score to evaluate long-range form and edit realization. Experiments demonstrate that MusicWeaver achieves state-of-the-art fidelity, controllability, and long-range coherence.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21714
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MusicWeaver: Composer-Style Structural Editing and Minute-Scale Coherent Music Generation
Wang, Xuanchen
Wang, Heng
Cai, Weidong
Sound
Multimedia
Recent advances in music generation produce impressive samples, however, practical creation still lacks two key capabilities: composer-style structural editing and minute-scale coherence. We present MusicWeaver, a framework for generating and editing long-range music using a human-interpretable intermediate representation with guaranteed edit locality. MusicWeaver decomposes generation into two stages: it first predicts a structured plan, a multi-level song program encoding musical attributes that composers can directly edit, and then renders audio conditioned on this plan. To ensure minute-scale coherence, we introduce a Global-Local Diffusion Transformer, where a global path captures long-range musical progression via compressed representations and memory, while a local path synthesizes fine-grained acoustic detail. We further propose a Motif Memory Retrieval module that enables consistent motif recurrence with controllable variation. For editing, we propose Projected Diffusion Inpainting, an inpainting method that denoises only user-specified regions and preserves unchanged content, allowing repeated edits without drift. Finally, we introduce Structure Coherence Score and Edit Fidelity Score to evaluate long-range form and edit realization. Experiments demonstrate that MusicWeaver achieves state-of-the-art fidelity, controllability, and long-range coherence.
title MusicWeaver: Composer-Style Structural Editing and Minute-Scale Coherent Music Generation
topic Sound
Multimedia
url https://arxiv.org/abs/2509.21714