用合成数据训练的端到端音乐识别模型，大幅降低错误率。
Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
- 通过合成数据生成与编码规范化提升训练效率
- 仅用6小时单卡训练，59M参数模型超越千亿参数基线
- 适合需要高精度音乐转录的研究者与开发者
光学音乐识别（OMR）将乐谱图像转为结构化文本，受限于真实扫描数据标注规模小，现有模型多依赖少样本迁移或简化的合成训练。另一挑战是编码非唯一性：在流行的Humdrum kern格式中，同一乐谱可对应多种文本表示，导致解码不确定性。本文提出Transcoda系统，采用（i）先进的合成数据生成流程，（ii）kern编码归一化以确保唯一标准形式，（iii）基于语法的解码保障输出语义正确性。该方法使一个仅5900万参数的模型在单个GPU上仅用6小时即可训练完成，性能超越数十亿参数基线。在新构建的合成乐谱基准上，其OMR-NED达18.46%，优于次优系统Legato的43.91%；在历史波兰乐谱数据集上，错误率从SMT++的80.16%降至63.97%。
原文摘要 · Abstract (English)
Optical Music Recognition (OMR), the task of transcribing sheet music into a structured textual representation, is currently bottlenecked by a lack of large-scale, annotated datasets of real scans. This forces models to rely on either few-shot transfer or synthetic training pipelines that remain overly simplistic. A secondary challenge is encoding non-uniqueness: in the popular Humdrum **kern format for transcribing music, multiple different text encodings can render into the same visual sheet music. This one-to-many mapping creates a harder learning task and introduces high uncertainty during decoding. We propose Transcoda, an OMR system built on (i) an advanced synthetic data generation pipeline, (ii) a normalization of the **kern encoding to enforce a unique normal form and (iii) grammar-based decoding to ensure the syntactic correctness of the output. This approach allows us to train a compact 59M-parameter model in just 6 hours on a single GPU that outperforms billion-parameter baselines. Transcoda achieves the best score among state of the art baselines on a newly curated benchmark of synthetically rendered scores at 18.46% OMR-NED (compared to 43.91% for the next-best system, Legato) and reduces the error rate on historical Polish scans to 63.97% OMR-NED (down from 80.16% for SMT++).
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。