用压缩算法生成音乐，速度快300倍，还能保证质量。
LZMidi: Compression-Based Symbolic Music Generation
- 基于LZ压缩算法构建概率模型，无需复杂训练
- 生成速度比扩散模型快300倍，训练快30倍
- 适合资源有限但需高效生成音乐的场景
近期符号化音乐生成多依赖Transformer、GAN和扩散模型等深度学习方法，虽效果优异但计算开销大。本文提出轻量级框架LZMidi，基于Lempel-Ziv（LZ78）诱导的序列概率分配（SPA），利用MIDI数据的离散有序结构，在标准CPU上实现高效音乐生成，训练与推理成本极低。理论上建立了该方法的普遍收敛性保障，证明其可靠稳健。相比先进扩散模型，LZMidi在弗雷彻音频距离（FAD）、沃尔什距离（WD）和相对熵（KL）评分上表现相当，同时显著降低计算负担：训练速度提升至多30倍，生成速度提升至多300倍。结果表明，通用压缩技术可高效建模与生成结构化序列数据，如符号化音乐，兼具实用性与理论严谨性。
原文摘要 · Abstract (English)
Recent advances in symbolic music generation primarily rely on deep learning models such as Transformers, GANs, and diffusion models. While these approaches achieve high-quality results, they require substantial computational resources, limiting their scalability. We introduce LZMidi, a lightweight symbolic music generation framework based on a Lempel-Ziv (LZ78)-induced sequential probability assignment (SPA). By leveraging the discrete and sequential structure of MIDI data, our approach enables efficient music generation on standard CPUs with minimal training and inference costs. Theoretically, we establish universal convergence guarantees for our approach, underscoring its reliability and robustness. Compared to state-of-the-art diffusion models, LZMidi achieves competitive Frechet Audio Distance (FAD), Wasserstein Distance (WD), and Kullback-Leibler (KL) scores, while significantly reducing computational overhead - up to 30x faster training and 300x faster generation. Our results position LZMidi as a significant advancement in compression-based learning, highlighting how universal compression techniques can efficiently model and generate structured sequential data, such as symbolic music, with practical scalability and theoretical rigor.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。