音乐音频生成模型教程：方法、系统与评估
A Tutorial on Generative Models for Music Audio
AI 导读
arXiv 2610.38252 发布的音乐音频生成模型长篇教程（monograph），面向熟悉神经网络训练的读者。内容涵盖神经音频编解码器与自编码器、自回归与掩码 token 模型、扩散与 flow matching、采样加速和偏好优化，并结合器乐生成、歌曲、编辑与现场演奏等应用讲解模型设计。
正文 · 原文
Abstract:Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that play alongside a musician in real time. This monograph explains the methods behind these systems for readers familiar with neural-network training who are new to music generation. It introduces neural audio codecs and autoencoders, autoregressive and masked token models, diffusion and flow matching, sampling acceleration, and preference optimization in a shared notation. Worked examples connect training objectives and sampling procedures to published systems. The application sections relate the musical requirements of instrumental generation, songs, editing, and live performance to model design. Comparison tables record representations, methods, inputs, tasks, and release information documented in papers and official sources. Symbolic composition, speech, and sound effects are included where they connect to music audio. We explain how to interpret automatic metrics and learned judges, design and report listening tests, and assess evidence about data provenance, memorization, attribution, and output detection. Selected legal decisions and disputes illustrate the implications for training and release. The reviewed systems combine established generative paradigms with new representations, planning stages, and post-training procedures. Differences in data, scale, and evaluation limit what cross-system comparisons can establish about the sources of reported gains.
| Subjects: | Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Multimedia (cs.MM); Sound (cs.SD) |
| MSC classes: | 68T07 (Primary), 68-02, 00A65, 94A12, 60J60 (Secondary) |
| ACM classes: | A.1; H.5.5; I.2.6; G.3; J.5 |
| Cite as: | arXiv:2610.38252 [eess.AS] |
| (or arXiv:2610.38252v1 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38252 arXiv-issued DOI via DataCite |
Submission history
From: Dorien Herremans [view email]
[v1]
Wed, 28 Oct 2026 04:04:24 UTC (307 KB)
来源：arXiv cs.AI · arxiv.org