arXiv cs.AI· Haoyu Gu, Lekai Qian, Haowu Zhou, Qi Liu, Shuai Wang·· 2 天前AI 评分27
BeatEdit：将符号音乐生成变为显式编辑
BeatEdit: Symbolic Music Generation as Explicit Editing
AI 导读
BeatEdit 是首个基于显式编辑操作的符号音乐生成框架，把生成重构为在草稿上编辑而非从零合成。它沿编辑密度递增轴整合了逐 token 序列标注纠错、迭代精修伴奏编辑和 tag-then-fill 片段补全三种机制，共享同一编码与预训练骨干，在三项任务上精度与感知质量均超过自回归和扩散方法，单次推理耗时不到 100 ms。
正文 · 原文
Abstract:Music creation is fundamentally a process of revision. Yet symbolic music generation remains dominated by paradigms that produce complete sequences from scratch, with limited support for selective modification. Edit-based methods have proven effective for text transformation tasks, but remain largely unexplored for symbolic music. We trace this absence to the representational level: conventional event-based music encodings lack the structural properties required by explicit music editing. In contrast, the BEAT encoding, a beat-grid-anchored representation originally designed for autoregressive generation, possesses structural properties amenable to editing. We propose BeatEdit, the first framework for symbolic music generation based on explicit edit operations, recasting generation as producing new content by editing a draft rather than synthesizing from scratch. BeatEdit comprises three complementary mechanisms along an axis of increasing edit density: per-token sequence tagging for error correction, iterative refinement for accompaniment editing, and tag-then-fill for segment completion. All these mechanisms share a single encoding and pre-trained backbone, achieving higher precision and perceptual quality than autoregressive and diffusion methods across all three tasks, while remaining efficient, with single-pass inference completing in under 100 ms. Cross-encoding evaluation further reveals that encoding design substantially influences editing effectiveness, with notable encoding-method interaction effects. Code is available at this https URL
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| ACM classes: | H.5.5; I.2.7 |
| Cite as: | arXiv:2607.11124 [cs.SD] |
| (or arXiv:2607.11124v3 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2607.11124 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3767308.3835589
DOI(s) linking to related resources |
Submission history
From: Haoyu Gu [view email]
[v1]
Mon, 13 Jul 2026 06:00:06 UTC (503 KB)
[v2]
Fri, 31 Jul 2026 09:19:35 UTC (531 KB)
[v3]
Thu, 15 Oct 2026 04:49:50 UTC (534 KB)
来源：arXiv cs.AI · arxiv.org