@inproceedings{kumar-etal-2014-translations,
title = "Translations of the Callhome {E}gyptian {A}rabic corpus for conversational speech translation",
author = "Kumar, Gaurav and
Cao, Yuan and
Cotterell, Ryan and
Callison-Burch, Chris and
Povey, Daniel and
Khudanpur, Sanjeev",
editor = {Federico, Marcello and
St{\"u}ker, Sebastian and
Yvon, Fran{\c{c}}ois},
booktitle = "Proceedings of the 11th International Workshop on Spoken Language Translation: Papers",
month = dec # " 4-5",
year = "2014",
address = "Lake Tahoe, California",
url = "https://aclanthology.org/2014.iwslt-papers.13",
pages = "244--248",
abstract = "Translation of the output of automatic speech recognition (ASR) systems, also known as speech translation, has received a lot of research interest recently. This is especially true for programs such as DARPA BOLT which focus on improving spontaneous human-human conversation across languages. However, this research is hindered by the dearth of datasets developed for this explicit purpose. For Egyptian Arabic-English, in particular, no parallel speechtranscription-translation dataset exists in the same domain. In order to support research in speech translation, we introduce the Callhome Egyptian Arabic-English Speech Translation Corpus. This supplements the existing LDC corpus with four reference translations for each utterance in the transcripts. The result is a three-way parallel dataset of Egyptian Arabic Speech, transcriptions and English translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2014-translations">
<titleInfo>
<title>Translations of the Callhome Egyptian Arabic corpus for conversational speech translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Povey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Khudanpur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-dec 4-5</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Workshop on Spoken Language Translation: Papers</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">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Lake Tahoe, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translation of the output of automatic speech recognition (ASR) systems, also known as speech translation, has received a lot of research interest recently. This is especially true for programs such as DARPA BOLT which focus on improving spontaneous human-human conversation across languages. However, this research is hindered by the dearth of datasets developed for this explicit purpose. For Egyptian Arabic-English, in particular, no parallel speechtranscription-translation dataset exists in the same domain. In order to support research in speech translation, we introduce the Callhome Egyptian Arabic-English Speech Translation Corpus. This supplements the existing LDC corpus with four reference translations for each utterance in the transcripts. The result is a three-way parallel dataset of Egyptian Arabic Speech, transcriptions and English translations.</abstract>
<identifier type="citekey">kumar-etal-2014-translations</identifier>
<location>
<url>https://aclanthology.org/2014.iwslt-papers.13</url>
</location>
<part>
<date>2014-dec 4-5</date>
<extent unit="page">
<start>244</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translations of the Callhome Egyptian Arabic corpus for conversational speech translation
%A Kumar, Gaurav
%A Cao, Yuan
%A Cotterell, Ryan
%A Callison-Burch, Chris
%A Povey, Daniel
%A Khudanpur, Sanjeev
%Y Federico, Marcello
%Y Stüker, Sebastian
%Y Yvon, François
%S Proceedings of the 11th International Workshop on Spoken Language Translation: Papers
%D 2014
%8 dec 4 5
%C Lake Tahoe, California
%F kumar-etal-2014-translations
%X Translation of the output of automatic speech recognition (ASR) systems, also known as speech translation, has received a lot of research interest recently. This is especially true for programs such as DARPA BOLT which focus on improving spontaneous human-human conversation across languages. However, this research is hindered by the dearth of datasets developed for this explicit purpose. For Egyptian Arabic-English, in particular, no parallel speechtranscription-translation dataset exists in the same domain. In order to support research in speech translation, we introduce the Callhome Egyptian Arabic-English Speech Translation Corpus. This supplements the existing LDC corpus with four reference translations for each utterance in the transcripts. The result is a three-way parallel dataset of Egyptian Arabic Speech, transcriptions and English translations.
%U https://aclanthology.org/2014.iwslt-papers.13
%P 244-248
Markdown (Informal)
[Translations of the Callhome Egyptian Arabic corpus for conversational speech translation](https://aclanthology.org/2014.iwslt-papers.13) (Kumar et al., IWSLT 2014)
ACL