@inproceedings{miller-etal-2021-corpus,
title = "Corpus Creation and Evaluation for Speech-to-Text and Speech Translation",
author = "Miller, Corey and
Tzoukermann, Evelyne and
Doyon, Jennifer and
Mallard, Elizabeth",
editor = "Campbell, Janice and
Huyck, Ben and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of Machine Translation Summit XVIII: Users and Providers Track",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-up.6",
pages = "44--53",
abstract = "The National Virtual Translation Center (NVTC) seeks to acquire human language technology (HLT) tools that will facilitate its mission to provide verbatim English translations of foreign language audio and video files. In the text domain, NVTC has been using translation memory (TM) for some time and has reported on the incorporation of machine translation (MT) into that workflow (Miller et al., 2020). While we have explored the use of speech-totext (STT) and speech translation (ST) in the past (Tzoukermann and Miller, 2018), we have now invested in the creation of a substantial human-made corpus to thoroughly evaluate alternatives. Results from our analysis of this corpus and the performance of HLT tools point the way to the most promising ones to deploy in our workflow.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miller-etal-2021-corpus">
<titleInfo>
<title>Corpus Creation and Evaluation for Speech-to-Text and Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Corey</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evelyne</namePart>
<namePart type="family">Tzoukermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Doyon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Mallard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XVIII: Users and Providers Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Huyck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The National Virtual Translation Center (NVTC) seeks to acquire human language technology (HLT) tools that will facilitate its mission to provide verbatim English translations of foreign language audio and video files. In the text domain, NVTC has been using translation memory (TM) for some time and has reported on the incorporation of machine translation (MT) into that workflow (Miller et al., 2020). While we have explored the use of speech-totext (STT) and speech translation (ST) in the past (Tzoukermann and Miller, 2018), we have now invested in the creation of a substantial human-made corpus to thoroughly evaluate alternatives. Results from our analysis of this corpus and the performance of HLT tools point the way to the most promising ones to deploy in our workflow.</abstract>
<identifier type="citekey">miller-etal-2021-corpus</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-up.6</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>44</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Creation and Evaluation for Speech-to-Text and Speech Translation
%A Miller, Corey
%A Tzoukermann, Evelyne
%A Doyon, Jennifer
%A Mallard, Elizabeth
%Y Campbell, Janice
%Y Huyck, Ben
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of Machine Translation Summit XVIII: Users and Providers Track
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F miller-etal-2021-corpus
%X The National Virtual Translation Center (NVTC) seeks to acquire human language technology (HLT) tools that will facilitate its mission to provide verbatim English translations of foreign language audio and video files. In the text domain, NVTC has been using translation memory (TM) for some time and has reported on the incorporation of machine translation (MT) into that workflow (Miller et al., 2020). While we have explored the use of speech-totext (STT) and speech translation (ST) in the past (Tzoukermann and Miller, 2018), we have now invested in the creation of a substantial human-made corpus to thoroughly evaluate alternatives. Results from our analysis of this corpus and the performance of HLT tools point the way to the most promising ones to deploy in our workflow.
%U https://aclanthology.org/2021.mtsummit-up.6
%P 44-53
Markdown (Informal)
[Corpus Creation and Evaluation for Speech-to-Text and Speech Translation](https://aclanthology.org/2021.mtsummit-up.6) (Miller et al., MTSummit 2021)
ACL