@article{brannon-etal-2023-dubbing,
title = "Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing",
author = "Brannon, William and
Virkar, Yogesh and
Thompson, Brian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "11",
year = "2023",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2023.tacl-1.25",
doi = "10.1162/tacl_a_00551",
pages = "419--435",
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 transfer of semantic properties such as emphasis and emotion, in automatic dubbing systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brannon-etal-2023-dubbing">
<titleInfo>
<title>Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Brannon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogesh</namePart>
<namePart type="family">Virkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<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 transfer of semantic properties such as emphasis and emotion, in automatic dubbing systems.</abstract>
<identifier type="citekey">brannon-etal-2023-dubbing</identifier>
<identifier type="doi">10.1162/tacl_a_00551</identifier>
<location>
<url>https://aclanthology.org/2023.tacl-1.25</url>
</location>
<part>
<date>2023</date>
<detail type="volume"><number>11</number></detail>
<extent unit="page">
<start>419</start>
<end>435</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing
%A Brannon, William
%A Virkar, Yogesh
%A Thompson, Brian
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F brannon-etal-2023-dubbing
%X 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 transfer of semantic properties such as emphasis and emotion, in automatic dubbing systems.
%R 10.1162/tacl_a_00551
%U https://aclanthology.org/2023.tacl-1.25
%U https://doi.org/10.1162/tacl_a_00551
%P 419-435
Markdown (Informal)
[Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing](https://aclanthology.org/2023.tacl-1.25) (Brannon et al., TACL 2023)
ACL