@inproceedings{wang-etal-2023-japanese,
title = "{J}apanese-to-{E}nglish Simultaneous Dubbing Prototype",
author = "Wang, Xiaolin and
Utiyama, Masao and
Sumita, Eiichiro",
editor = "Bollegala, Danushka and
Huang, Ruihong and
Ritter, Alan",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-demo.16",
doi = "10.18653/v1/2023.acl-demo.16",
pages = "169--178",
abstract = "Live video streaming has become an important form of communication such as virtual conferences. However, for cross-language communication in live video streaming, reading subtitles degrades the viewing experience. To address this problem, our simultaneous dubbing prototype translates and replaces the original speech of a live video stream in a simultaneous manner. Tests on a collection of 90 public videos show that our system achieves a low average latency of 11.90 seconds for smooth playback. Our method is general and can be extended to other language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-japanese">
<titleInfo>
<title>Japanese-to-English Simultaneous Dubbing Prototype</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaolin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Live video streaming has become an important form of communication such as virtual conferences. However, for cross-language communication in live video streaming, reading subtitles degrades the viewing experience. To address this problem, our simultaneous dubbing prototype translates and replaces the original speech of a live video stream in a simultaneous manner. Tests on a collection of 90 public videos show that our system achieves a low average latency of 11.90 seconds for smooth playback. Our method is general and can be extended to other language pairs.</abstract>
<identifier type="citekey">wang-etal-2023-japanese</identifier>
<identifier type="doi">10.18653/v1/2023.acl-demo.16</identifier>
<location>
<url>https://aclanthology.org/2023.acl-demo.16</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>169</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Japanese-to-English Simultaneous Dubbing Prototype
%A Wang, Xiaolin
%A Utiyama, Masao
%A Sumita, Eiichiro
%Y Bollegala, Danushka
%Y Huang, Ruihong
%Y Ritter, Alan
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-japanese
%X Live video streaming has become an important form of communication such as virtual conferences. However, for cross-language communication in live video streaming, reading subtitles degrades the viewing experience. To address this problem, our simultaneous dubbing prototype translates and replaces the original speech of a live video stream in a simultaneous manner. Tests on a collection of 90 public videos show that our system achieves a low average latency of 11.90 seconds for smooth playback. Our method is general and can be extended to other language pairs.
%R 10.18653/v1/2023.acl-demo.16
%U https://aclanthology.org/2023.acl-demo.16
%U https://doi.org/10.18653/v1/2023.acl-demo.16
%P 169-178
Markdown (Informal)
[Japanese-to-English Simultaneous Dubbing Prototype](https://aclanthology.org/2023.acl-demo.16) (Wang et al., ACL 2023)
ACL
- Xiaolin Wang, Masao Utiyama, and Eiichiro Sumita. 2023. Japanese-to-English Simultaneous Dubbing Prototype. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 169–178, Toronto, Canada. Association for Computational Linguistics.