@inproceedings{federico-etal-2020-speech,
title = "From Speech-to-Speech Translation to Automatic Dubbing",
author = "Federico, Marcello and
Enyedi, Robert and
Barra-Chicote, Roberto and
Giri, Ritwik and
Isik, Umut and
Krishnaswamy, Arvindh and
Sawaf, Hassan",
editor = {Federico, Marcello and
Waibel, Alex and
Knight, Kevin and
Nakamura, Satoshi and
Ney, Hermann and
Niehues, Jan and
St{\"u}ker, Sebastian and
Wu, Dekai and
Mariani, Joseph and
Yvon, Francois},
booktitle = "Proceedings of the 17th International Conference on Spoken Language Translation",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.iwslt-1.31",
doi = "10.18653/v1/2020.iwslt-1.31",
pages = "257--264",
abstract = "We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of the translation with the original speech segments, neural text-to-speech with fine tuning of the duration of each utterance, and, finally, audio rendering to enriches text-to-speech output with background noise and reverberation extracted from the original audio. We report and discuss results of a first subjective evaluation of automatic dubbing of excerpts of TED Talks from English into Italian, which measures the perceived naturalness of automatic dubbing and the relative importance of each proposed enhancement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="federico-etal-2020-speech">
<titleInfo>
<title>From Speech-to-Speech Translation to Automatic Dubbing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Enyedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Barra-Chicote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritwik</namePart>
<namePart type="family">Giri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Umut</namePart>
<namePart type="family">Isik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvindh</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dekai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francois</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of the translation with the original speech segments, neural text-to-speech with fine tuning of the duration of each utterance, and, finally, audio rendering to enriches text-to-speech output with background noise and reverberation extracted from the original audio. We report and discuss results of a first subjective evaluation of automatic dubbing of excerpts of TED Talks from English into Italian, which measures the perceived naturalness of automatic dubbing and the relative importance of each proposed enhancement.</abstract>
<identifier type="citekey">federico-etal-2020-speech</identifier>
<identifier type="doi">10.18653/v1/2020.iwslt-1.31</identifier>
<location>
<url>https://aclanthology.org/2020.iwslt-1.31</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>257</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Speech-to-Speech Translation to Automatic Dubbing
%A Federico, Marcello
%A Enyedi, Robert
%A Barra-Chicote, Roberto
%A Giri, Ritwik
%A Isik, Umut
%A Krishnaswamy, Arvindh
%A Sawaf, Hassan
%Y Federico, Marcello
%Y Waibel, Alex
%Y Knight, Kevin
%Y Nakamura, Satoshi
%Y Ney, Hermann
%Y Niehues, Jan
%Y Stüker, Sebastian
%Y Wu, Dekai
%Y Mariani, Joseph
%Y Yvon, Francois
%S Proceedings of the 17th International Conference on Spoken Language Translation
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F federico-etal-2020-speech
%X We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of the translation with the original speech segments, neural text-to-speech with fine tuning of the duration of each utterance, and, finally, audio rendering to enriches text-to-speech output with background noise and reverberation extracted from the original audio. We report and discuss results of a first subjective evaluation of automatic dubbing of excerpts of TED Talks from English into Italian, which measures the perceived naturalness of automatic dubbing and the relative importance of each proposed enhancement.
%R 10.18653/v1/2020.iwslt-1.31
%U https://aclanthology.org/2020.iwslt-1.31
%U https://doi.org/10.18653/v1/2020.iwslt-1.31
%P 257-264
Markdown (Informal)
[From Speech-to-Speech Translation to Automatic Dubbing](https://aclanthology.org/2020.iwslt-1.31) (Federico et al., IWSLT 2020)
ACL
- Marcello Federico, Robert Enyedi, Roberto Barra-Chicote, Ritwik Giri, Umut Isik, Arvindh Krishnaswamy, and Hassan Sawaf. 2020. From Speech-to-Speech Translation to Automatic Dubbing. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 257–264, Online. Association for Computational Linguistics.