Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing

TL;DR

This large-scale study of human dubbing reveals that vocal naturalness and translation quality are more crucial than lip-sync or timing constraints, highlighting new directions for automatic dubbing research.

Contribution

It provides the first extensive analysis of human dubbing practices using a large corpus, challenging existing assumptions and emphasizing the importance of speech characteristics and semantic transfer.

Findings

Vocal naturalness and translation quality are prioritized over lip-sync.

Source audio influences dubbing beyond translation words.

Research should focus on preserving speech characteristics and emotion.

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.