用GAN生成逼真手写乐谱，提升音乐识别系统数据质量
Synthesising Handwritten Music with GANs: A Comprehensive Evaluation of CycleWGAN, ProGAN, and DCGAN
- 引入循环WGAN增强风格迁移与训练稳定性
- FID 41.87、IS 2.29、KID 0.05，生成质量领先
- 适合需要高质量手写乐谱数据的研究者
手写乐谱的生成是提升光学音乐识别（OMR）系统性能的关键步骤，但档案中的手写乐谱因脆弱性、书写风格多样及图像质量差异，难以数字化。本文利用生成对抗网络（GAN）解决数据稀缺问题，全面评估DCGAN、ProGAN和CycleWGAN三种模型在生成多样化、高质量手写乐谱图像上的表现。所提出的CycleWGAN模型通过增强风格迁移与训练稳定性，在定性和定量评估中均显著优于其他模型。其在测试集上取得FID 41.87、IS 2.29、KID 0.05的优异结果，为改进OMR系统提供了有效数据生成方案。
原文摘要 · Abstract (English)
The generation of handwritten music sheets is a crucial step toward enhancing Optical Music Recognition (OMR) systems, which rely on large and diverse datasets for optimal performance. However, handwritten music sheets, often found in archives, present challenges for digitisation due to their fragility, varied handwriting styles, and image quality. This paper addresses the data scarcity problem by applying Generative Adversarial Networks (GANs) to synthesise realistic handwritten music sheets. We provide a comprehensive evaluation of three GAN models - DCGAN, ProGAN, and CycleWGAN - comparing their ability to generate diverse and high-quality handwritten music images. The proposed CycleWGAN model, which enhances style transfer and training stability, significantly outperforms DCGAN and ProGAN in both qualitative and quantitative evaluations. CycleWGAN achieves superior performance, with an FID score of 41.87, an IS of 2.29, and a KID of 0.05, making it a promising solution for improving OMR systems.
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。