arXiv cs.AI· Congren Dai, Zhancheng Guo, Danni Zhao, Wenchu Wang, Xiaobing Li, Maosong Sun·· 4 小时前AI 评分28
OmniScore-Bench:评估视觉语言模型的乐谱阅读能力
OmniScore-Bench: Evaluating Vision-Language Models on Musical Score Reading
AI 导读
研究者推出 OmniScore-Bench,通过 3,000 道覆盖六大方面、24 种任务子类型的题目评估视觉语言模型(VLM)的乐谱识别与理解能力。对 12 个 VLM 的测评显示,不同模型在不同乐谱任务上的能力各有差异,转录领先者因单页、多页等任务而不同。基准还支持自动评估符号定位、音乐一致性及证据关联问答,用于诊断模型哪些读谱操作可靠、哪些仍需改进。
正文 · 原文
Abstract:Vision-language models (VLMs) can answer questions about musical scores, but their ability to recognise notation, recover its structure and interpret its musical meaning requires separate evaluation. Existing optical music recognition (OMR) resources establish detection and transcription measurements; a transcription score alone leaves the strengths and bottlenecks of a VLM score reader unresolved. We introduce OmniScore-Bench, an evaluation of OMR capabilities in VLMs through 3,000 questions spanning six aspects and 24 task subtypes. Each question specifies a visible scope, reference annotations and an answer schema, enabling automatic evaluation from symbol localisation to musical consistency and evidence-linked question answering. Our assessment of twelve VLMs reveals operation-specific capability profiles and different transcription leaders across excerpt, single-page and multipage tasks. Controlled analyses examine the roles of score images, auxiliary givens and additional page context. On the tested subset, image removal exposes visual dependence in pitch and repeat interpretation while measuring how much performance remains with public context alone. Separate format and content analyses distinguish answer-format violations from musical errors. OmniScore-Bench supports diagnosing which score-reading operations VLMs perform reliably and which require improvement.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17870 [cs.AI] |
| (or arXiv:2611.17870v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17870 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Congren Dai [view email]
[v1]
Fri, 13 Nov 2026 08:01:19 UTC (860 KB)
来源:arXiv cs.AI · arxiv.org