BeatEdit：作为显式编辑的符号音乐生成
BeatEdit: Symbolic Music Generation as Explicit Editing
浏览论文内容
中文总结 AI 辅助
研究针对符号音乐生成中缺乏选择性修改支持的问题，提出BeatEdit框架，基于BEAT编码，含三种互补机制，共享单一编码和预训练主干，在多项任务中精度和质量更高且高效，揭示编码设计对编辑有效性有重要影响。
中文摘要 AI 辅助
音乐创作本质上是一个修订过程。然而，符号音乐生成仍主要由从头生成完整序列的范式主导，对选择性修改的支持有限。基于编辑的方法在文本转换任务中已证明有效，但在符号音乐方面基本未被探索。我们将这种缺失追溯到表示层面：传统的基于事件的音乐编码缺乏显式音乐编辑所需的结构属性。相比之下，BEAT编码是一种最初为自回归生成设计的基于节拍网格的表示，具有适合编辑的结构属性。我们提出了BeatEdit，这是第一个基于显式编辑操作的符号音乐生成框架，将生成重新定义为通过编辑草稿而不是从头合成来产生新内容。BeatEdit包括沿编辑密度增加轴的三种互补机制：用于纠错的逐令牌序列标记、用于伴奏编辑的迭代细化以及用于片段完成 的标记然后填充。所有这些机制共享单一编码和预训练主干，在所有三项任务中比自回归和扩散方法实现更高的精度和感知质量，同时保持高效，单通道推理在100毫秒内完成。交叉编码评估进一步表明，编码设计对编辑有效性有重大影响，存在显著的编码方法交互效应。代码可在这个https URL获取。
英文摘要
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 https://github.com/Haoyu-Gu/BeatEdit-code
发表机构
- School of Future Technology South China University of Technology Guangzhou China（未来技术学院 华南理工大学 广州 中国）
- South China University of Technology（华南理工大学）
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
