arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.02684cs.HC
收藏

ADx3:高质量可及音频描述的协作流程

ADx3: A Collaborative Workflow for High-Quality Accessible Audio Description

Northeastern University(东北大学);Smith-Kettlewell Eye Research Institute(史密斯-凯特尔韦尔眼科研究所);San Francisco State University(旧金山州立大学)

Lana Do, Shasta Ihorn, Charity Pitcher-Cooper, Juvenal Francisco Barajas, Gio Jung, Xuan Duy Anh Nguyen, Sanjay Mirani, Ilmi Yoon

AI总结:

ADx3通过整合GenAD、RefineAD和AdaptAD模块,实现高质量可及音频描述的协作流程,提升描述质量和用户交互体验。

摘要:

音频描述(AD)使视频内容对视障和低视力(BLV)观众具有可及性,但生成高质量的描述需要大量资源。自动化AD提供了可扩展性,先前研究显示人类在循环编辑和用户查询可以有效提升叙述质量。我们介绍了ADx3,一种新的框架,整合了三个模块:GenAD,通过基于可及性指导的提示提升基线描述生成,利用现代视觉语言模型(VLMs);RefineAD,支持BLV和视力正常用户通过包容性界面查看和编辑草稿;AdaptAD,允许按需用户查询。我们评估了GenAD,在一项研究中,七位可及性专家使用专业指南审查VLM生成的描述。发现显示,通过定制提示,VLMs可以生成符合基本标准的描述,但优秀的描述需要人类编辑(RefineAD)和互动(AdaptAD)。ADx3展示了可及内容创建的协作流程,其中组件相互增强并实现持续改进:编辑指导未来的基线,用户查询揭示了AI生成和人工撰写的描述之间的差距。

英文摘要:

Audio description (AD) makes video content accessible to blind and low-vision (BLV) audiences, but producing high-quality descriptions is resource-intensive. Automated AD offers scalability, and prior studies show human-in-the-loop editing and user queries effectively improve narration. We introduce ADx3, a novel framework integrating these three modules: GenAD, upgrading baseline description generation with modern vision-language models (VLMs) guided by accessibility-informed prompting; RefineAD, supporting BLV and sighted users to view and edit drafts through an inclusive interface; and AdaptAD, enabling on-demand user queries. We evaluated GenAD in a study where seven accessibility specialists reviewed VLM-generated descriptions using professional guidelines. Findings show that with tailored prompting, VLMs produce good descriptions meeting basic standards, but excellent descriptions require human edits (RefineAD) and interaction (AdaptAD). ADx3 demonstrates collaborative workflows for accessible content creation, where components reinforce one another and enable continuous improvement: edits guide future baselines and user queries reveal gaps in AI-generated and human-authored descriptions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑