# Exploring Community-Driven Descriptions for Making Livestreams Accessible

arXiv: https://arxiv.org/abs/2310.07057 · HTML: https://mlsanity.com/paper/2310.07057/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2023.

## Built on by (most cited first, 1 of 1)

- [Making Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video Player](https://mlsanity.com/paper/2602.04104/) (2026)

## Abstract (arXiv)

People watch livestreams to connect with others and learn about their hobbies. Livestreams feature multiple visual streams including the main video, webcams, on-screen overlays, and chat, all of which are inaccessible to livestream viewers with visual impairments. While prior work explores creating audio descriptions for recorded videos, live videos present new challenges: authoring descriptions in real-time, describing domain-specific content, and prioritizing which complex visual information to describe. We explore inviting livestream community members who are domain experts to provide live descriptions. We first conducted a study with 18 sighted livestream community members authoring descriptions for livestreams using three different description methods: live descriptions using text, live descriptions using speech, and asynchronous descriptions using text. We then conducted a study with 9 livestream community members with visual impairments, who shared their current strategies and challenges for watching livestreams and provided feedback on the community-written descriptions. We conclude with implications for improving the accessibility of livestreams.