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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Yingqiang, Fischer, Lukas, Lintner, Alexa, Ebling, Sarah
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917800741699584
author Gao, Yingqiang
Fischer, Lukas
Lintner, Alexa
Ebling, Sarah
author_facet Gao, Yingqiang
Fischer, Lukas
Lintner, Alexa
Ebling, Sarah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08860
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies
Gao, Yingqiang
Fischer, Lukas
Lintner, Alexa
Ebling, Sarah
Computation and Language
Computer Vision and Pattern Recognition
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.
title Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.08860