Andha-Dhun: A First Look at Audio Descriptions in Hindi

2026-07-07

AI Summary

This study addresses the scarcity of Hindi audio description (AD) resources for blind and low-vision individuals in India by introducing Andha-Dhun, the first dataset comprising human-authored AD for eight full-length films in Hindi. The work systematically compares two generation approaches: direct synthesis from English dense video captions and translation of existing English AD into Hindi. Employing natural language generation metrics, machine translation evaluation, LLM-as-a-judge assessments, and perplexity analysis, the study finds that while human translation outperforms machine translation, it still struggles to preserve cultural appropriateness and expressive diversity. In contrast, natively produced Hindi AD demonstrates significantly superior accessibility, cultural alignment, and linguistic richness for local audiences, underscoring the necessity of localized AD creation over reliance on source-language fidelity alone.

Abstract

Audio Descriptions (ADs) narrate visual content for Blind and Low Vision (BLV) audiences during gaps in audiovisual media. There is growing momentum around ADs in movies and TV shows, and with mandates from India's Central Board of Film Certification (CBFC), there is a need to expand ADs beyond English. Yet, there is no work that generates ADs for any Indian language. To address this gap, we present the first systematic study of ADs in Hindi, contributing to aspects such as data, generation, and evaluation. We introduce Andha-Dhun, the first dataset of human-authored Hindi ADs collected from 8 full-length movies. We explore two approaches for generating ADs in Hindi: (i) directly from English dense video descriptions, and (ii) translating English ADs into Hindi. We evaluate these approaches using perplexity and LLM-as-a-judge metrics to assess fluency and quality respectively. We also analyze movies that have both English and Hindi human-authored ADs and find that naive translation introduces artifacts and narrows diversity compared to original Hindi ADs. Direct machine translation fails to adapt cultural references, while human-translated ADs do better but still fall short. Our findings emphasize that the purpose of Hindi ADs is accessibility for Indian BLV audiences, and that this requires adapting content for the audience more than strict fidelity to the source.

Problem

• Audio Description
• Hindi
• Accessibility
• Blind and Low Vision
• Indian Languages

Innovation

• Audio Description
• Hindi
• Accessibility
• Machine Translation
• Dataset