BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion

TL;DR

BOOM is a multimodal multilingual lecture system that translates and localizes audio and slides, providing synchronized outputs across text, slides, and speech to enhance accessibility and downstream educational tasks.

Contribution

It introduces an end-to-end multimodal translation system that preserves all lecture modalities, enabling comprehensive multilingual access to educational content.

Findings

Slide-aware transcripts improve summarization accuracy

The system effectively localizes slides with visual preservation

End-to-end approach benefits downstream tasks like question answering

Abstract

The globalization of education and rapid growth of online learning have made localizing educational content a critical challenge. Lecture materials are inherently multimodal, combining spoken audio with visual slides, which requires systems capable of processing multiple input modalities. To provide an accessible and complete learning experience, translations must preserve all modalities: text for reading, slides for visual understanding, and speech for auditory learning. We present \textbf{BOOM}, a multimodal multilingual lecture companion that jointly translates lecture audio and slides to produce synchronized outputs across three modalities: translated text, localized slides with preserved visual elements, and synthesized speech. This end-to-end approach enables students to access lectures in their native language while aiming to preserve the original content in its entirety. Our experiments demonstrate that slide-aware transcripts also yield cascading benefits for downstream tasks such as summarization and question answering. The demo video and code can be found at https://ai4lt.github.io/boom/ \footnote{All released code and models are licensed under the MIT License}.