用大模型生成爵士钢琴新变奏，保持原曲结构。
Exploring Transformer-Based Music Overpainting for Jazz Piano Variations
- 用Transformer模型实现音乐再创作，保留旋律与和声
- 在4352对数据上训练，泛化能力优于小数据集
- 适合音乐生成与人工智能作曲研究者
本文探索基于Transformer的音乐过涂（music overpainting）方法，聚焦爵士钢琴变奏生成。该任务旨在生成新变奏的同时保留输入的旋律与和声结构。现有方法受限于小规模数据集，难以扩展与多样化。为此，我们构建了VAR4000——一个大型爵士钢琴演奏数据集的子集，包含4,352个训练样本对。通过半自动流程，我们在该数据集上评估两种Transformer配置，并与更小的JAZZVAR数据集进行对比。初步结果表明，使用更大数据集时模型在泛化能力和性能上均有显著提升，验证了基于Transformer的方法在更大、更丰富数据集上的有效扩展潜力。
原文摘要 · Abstract (English)
This paper explores transformer-based models for music overpainting, focusing on jazz piano variations. Music overpainting generates new variations while preserving the melodic and harmonic structure of the input. Existing approaches are limited by small datasets, restricting scalability and diversity. We introduce VAR4000, a subset of a larger dataset for jazz piano performances, consisting of 4,352 training pairs. Using a semi-automatic pipeline, we evaluate two transformer configurations on VAR4000, comparing their performance with the smaller JAZZVAR dataset. Preliminary results show promising improvements in generalisation and performance with the larger dataset configuration, highlighting the potential of transformer models to scale effectively for music overpainting on larger and more diverse datasets.
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。