Applying Automated Machine Translation to Educational Video Courses

TL;DR

This paper explores using advanced machine translation and speech synthesis to automatically translate educational videos, improving accessibility and reducing human effort through confidence estimation and user feedback.

Contribution

It introduces a complete system for translating educational videos with confidence estimators and iterative improvement, advancing automated video translation methods.

Findings

Effective translation confidence estimators were developed.

Automated system successfully delivered translated videos with user feedback integration.

Reduced human translation effort in educational content localization.

Abstract

We studied the capability of automated machine translation in the online video education space by automatically translating Khan Academy videos with state-of-the-art translation models and applying text-to-speech synthesis and audio/video synchronization to build engaging videos in target languages. We also analyzed and established two reliable translation confidence estimators based on round-trip translations in order to efficiently manage translation quality and reduce human translation effort. Finally, we developed a deployable system to deliver translated videos to end users and collect user corrections for iterative improvement.