English(EN) MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning

新的MMAC基准评估AudioLLMs的字幕可靠性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-31 04:00

研究人员推出MMAC，一个旨在跨多个维度评估音频字幕模型的新基准。该基准包含来自不同来源的5,638个音频片段，并根据15个评估维度和6个能力类别的信信息覆盖率和可靠性来评估字幕。使用MMAC进行的初步评估显示，开源和专有的AudioLLMs在性能上存在显著差异。 AI

影响该基准有望催生更强大、更可靠的音频字幕模型，从而改进依赖于理解和描述音频内容的应用程序。

排序理由该条目描述了一个用于评估AI模型的新学术基准。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个用于评估AI模型的新学术基准。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 46 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Weijie Wu, Junbo Li, Lin Li, Jun Fang, Qingyang Hong · 2026-07-31 04:00

MMAC：一个用于音频字幕的大规模多维度基准测试

arXiv:2607.27109v2 Announce Type: cross Abstract: With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation qual…