Dubbing In Practice: A Large Scale Study Of Human Localization With Insights For Automatic Dubbing

Abstract

We investigate how humans perform the task of dubbing video content from one language into another, leveraging a novel corpus of 319.57 hours of video from 54 professionally produced titles. This is the first such large-scale study we are aware of. The results challenge a number of assumptions commonly made in both qualitative literature on human dubbing and machine-learning literature on automatic dubbing, arguing for the importance of vocal naturalness and translation quality over commonly emphasized isometric (character length) and lip-sync constraints, and for a more qualified view of the importance of isochronic (timing) constraints. We also find substantial influence of the source-side audio on human dubs through channels other than the words of the translation, pointing to the need for research on ways to preserve speech characteristics, as well as semantic transfer such as emphasis/emotion, in automatic dubbing systems.

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keybrannon2022dubbing

Related papers

• Large-scale Multilingual Audio Visual Dubbing (2020)0.00
• ANIM-400K: A Large-scale Dataset For Automated End-to-end Dubbing Of Video (2024)8.65
• Prosody-enhanced Acoustic Pre-training And Acoustic-disentangled Prosody Adapting For Movie Dubbing (2025)3.58
• Learning To Dub Movies Via Hierarchical Prosody Models (2022)10.97
• Voicecraft-dub: Automated Video Dubbing With Neural Codec Language Models (2025)0.00
• Neural Dubber: Dubbing For Videos According To Scripts (2021)0.00
• Videodubber: Machine Translation With Speech-aware Length Control For Video Dubbing (2022)8.82
• Isochrony-aware Neural Machine Translation For Automatic Dubbing (2021)5.24