BetterSub

Document Type

Abstract

Publication Date

Fall 12-1-2024

Abstract

Inaccurate subtitles due to poor audio quality can lead to misunderstandings and hinder accessibility for viewers, particularly those who are deaf, or hard of hearing. BetterSub addresses these challenges by enhancing subtitle accuracy through the integration of traditional audio transcription and lip-reading technology. By analyzing both audio inputs and visual cues from lip movements with computer vision techniques, BetterSub provides more coherent and reliable subtitles, making content more accessible to more diverse audiences. This project not only demonstrates the practical application of machine learning and computer vision techniques but also has the potential to significantly improve accessibility for the deaf and hard-of-hearing community, as well as enhance the viewing experience for all users in various scenarios.

Comments

Completed as part of the Computer Science Senior Capstone Project.

This document is currently not available here.

Share

COinS