CLCVOct 11, 2024

Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies

arXiv:2410.08860v113 citationsh-index: 1NAACL
Originality Synthesis-oriented
AI Analysis

It addresses the problem of costly and time-consuming audio description generation for accessibility, but it is incremental as it reviews existing technologies rather than proposing new methods.

This paper reviews how large language models (LLMs) and vision-language models (VLMs) can be applied to generate audio descriptions (ADs) for blind and visually impaired individuals, aiming to reduce the time and cost of manual AD creation.

Audio descriptions (ADs) function as acoustic commentaries designed to assist blind persons and persons with visual impairments in accessing digital media content on television and in movies, among other settings. As an accessibility service typically provided by trained AD professionals, the generation of ADs demands significant human effort, making the process both time-consuming and costly. Recent advancements in natural language processing (NLP) and computer vision (CV), particularly in large language models (LLMs) and vision-language models (VLMs), have allowed for getting a step closer to automatic AD generation. This paper reviews the technologies pertinent to AD generation in the era of LLMs and VLMs: we discuss how state-of-the-art NLP and CV technologies can be applied to generate ADs and identify essential research directions for the future.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes