The paper introduces Andha-Dhun, the first Hindi audio description dataset, and shows that direct generation from dense captions outperforms translation of English ADs, while machine translation fails to resolve cultural references.
LLM-AD: Large Language Model based Audio Description System
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
The development of Audio Description (AD) has been a pivotal step forward in making video content more accessible and inclusive. Traditionally, AD production has demanded a considerable amount of skilled labor, while existing automated approaches still necessitate extensive training to integrate multimodal inputs and tailor the output from a captioning style to an AD style. In this paper, we introduce an automated AD generation pipeline that harnesses the potent multimodal and instruction-following capacities of GPT-4V(ision). Notably, our methodology employs readily available components, eliminating the need for additional training. It produces ADs that not only comply with established natural language AD production standards but also maintain contextually consistent character information across frames, courtesy of a tracking-based character recognition module. A thorough analysis on the MAD dataset reveals that our approach achieves a performance on par with learning-based methods in automated AD production, as substantiated by a CIDEr score of 20.5.
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
support 1representative citing papers
READ is the first reinforcement-learning framework for training audio-description generators, using sequence-level rewards for reference match, length, format, and context-aware coherence.
AI drafts for audio description reduce editing time and cognitive load only when they exceed a content-dependent quality threshold, unlike unguided baseline drafts.
citing papers explorer
-
Andha-Dhun: A First Look at Audio Descriptions in Hindi
The paper introduces Andha-Dhun, the first Hindi audio description dataset, and shows that direct generation from dense captions outperforms translation of English ADs, while machine translation fails to resolve cultural references.
-
READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations
READ is the first reinforcement-learning framework for training audio-description generators, using sequence-level rewards for reference match, length, format, and context-aware coherence.
-
Making AI Drafts Count: A Quality Threshold in Audio Description Workflows
AI drafts for audio description reduce editing time and cognitive load only when they exceed a content-dependent quality threshold, unlike unguided baseline drafts.