Papers with automatic AD generation
Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies (2025.findings-naacl)
Copied to clipboard
| Challenge: | Audio descriptions (ADs) are acoustic commentaries designed to assist blind and visually impaired individuals in accessing digital media content. |
| Approach: | They examine how state-of-the-art NLP and CV technologies can be applied to generate ADs . they identify essential research directions for the future . |
| Outcome: | The proposed technologies can be applied to generate audio descriptions (ADs) the process is time-consuming and costly, and requires significant human effort . the authors identify key research directions for the future . |
What You See is What You Ask: Evaluating Audio Descriptions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies evaluate audio descriptions (ADs) using trimmed clips, but writing them is subjective. |
| Approach: | They propose a QA benchmark that evaluates audio descriptions at the level of short, coherent video segments. |
| Outcome: | The proposed evaluation paradigm addresses two themes central to ADs . it compares two humannarrated AD tracks and shows that current methods lag behind human-authored ADs. |