Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.05348 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913096869609472 |
|---|---|
| author | Do, Lana Ihorn, Shasta Pitcher-Cooper, Charity M. Mirani, Sanjay Jung, Gio Shim, Hyunjoo Qin, Zhenzhen Nguyen, Kien T. Athitsos, Vassilis Yoon, Ilmi |
| author_facet | Do, Lana Ihorn, Shasta Pitcher-Cooper, Charity M. Mirani, Sanjay Jung, Gio Shim, Hyunjoo Qin, Zhenzhen Nguyen, Kien T. Athitsos, Vassilis Yoon, Ilmi |
| contents | Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing process. We investigate this through GenAD, an AD generation pipeline that incorporates accessibility guidelines and contextual video information, and RefineAD, an editing interface for human revisions. Human-AI contributions are measured across text, timing, and delivery. In a within-subjects study, we compared authoring from scratch against editing AI drafts of varying quality. GenAD drafts cut completion time by more than half and significantly reduced cognitive load. In contrast, baseline drafts generated from simple, unguided prompts offered only modest benefits, pointing to a minimum quality threshold for effectiveness. Qualitative findings suggest this threshold is content-dependent; as visual complexity increases, so does the quality needed from AI drafts. We propose this as a design principle: effective AI assistance should clear a quality threshold suited to the target content, rather than simply be present. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Making AI Drafts Count: A Quality Threshold in Audio Description Workflows Do, Lana Ihorn, Shasta Pitcher-Cooper, Charity M. Mirani, Sanjay Jung, Gio Shim, Hyunjoo Qin, Zhenzhen Nguyen, Kien T. Athitsos, Vassilis Yoon, Ilmi Human-Computer Interaction Artificial Intelligence Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing process. We investigate this through GenAD, an AD generation pipeline that incorporates accessibility guidelines and contextual video information, and RefineAD, an editing interface for human revisions. Human-AI contributions are measured across text, timing, and delivery. In a within-subjects study, we compared authoring from scratch against editing AI drafts of varying quality. GenAD drafts cut completion time by more than half and significantly reduced cognitive load. In contrast, baseline drafts generated from simple, unguided prompts offered only modest benefits, pointing to a minimum quality threshold for effectiveness. Qualitative findings suggest this threshold is content-dependent; as visual complexity increases, so does the quality needed from AI drafts. We propose this as a design principle: effective AI assistance should clear a quality threshold suited to the target content, rather than simply be present. |
| title | Making AI Drafts Count: A Quality Threshold in Audio Description Workflows |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2605.05348 |