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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koneru, Sai, Retkowski, Fabian, Huber, Christian, Hilgert, Lukas, Akti, Seymanur, Ugan, Enes Yavuz, Waibel, Alexander, Niehues, Jan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908845406683136
author Koneru, Sai
Retkowski, Fabian
Huber, Christian
Hilgert, Lukas
Akti, Seymanur
Ugan, Enes Yavuz
Waibel, Alexander
Niehues, Jan
author_facet Koneru, Sai
Retkowski, Fabian
Huber, Christian
Hilgert, Lukas
Akti, Seymanur
Ugan, Enes Yavuz
Waibel, Alexander
Niehues, Jan
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion
Koneru, Sai
Retkowski, Fabian
Huber, Christian
Hilgert, Lukas
Akti, Seymanur
Ugan, Enes Yavuz
Waibel, Alexander
Niehues, Jan
Computation and Language
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}.
title BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion
topic Computation and Language
url https://arxiv.org/abs/2512.02817