@inproceedings{stuker-etal-2012-kit,
title = "The {KIT} Lecture Corpus for Speech Translation",
author = {St{\"u}ker, Sebastian and
Kraft, Florian and
Mohr, Christian and
Herrmann, Teresa and
Cho, Eunah and
Waibel, Alex},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1121_Paper.pdf",
pages = "3409--3414",
abstract = "Academic lectures offer valuable content, but often do not reach their full potential audience due to the language barrier. Human translations of lectures are too expensive to be widely used. Speech translation technology can be an affordable alternative in this case. State-of-the-art speech translation systems utilize statistical models that need to be trained on large amounts of in-domain data. In order to support the KIT lecture translation project in its effort to introduce speech translation technology in KIT's lecture halls, we have collected a corpus of German lectures at KIT. In this paper we describe how we recorded the lectures and how we annotated them. We further give detailed statistics on the types of lectures in the corpus and its size. We collected the corpus with the purpose in mind that it should not just be suited for training a spoken language translation system the traditional way, but should also enable us to research techniques that enable the translation system to automatically and autonomously adapt itself to the varying topics and speakers of lectures",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stuker-etal-2012-kit">
<titleInfo>
<title>The KIT Lecture Corpus for Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Kraft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Mohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Herrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunah</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</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">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Academic lectures offer valuable content, but often do not reach their full potential audience due to the language barrier. Human translations of lectures are too expensive to be widely used. Speech translation technology can be an affordable alternative in this case. State-of-the-art speech translation systems utilize statistical models that need to be trained on large amounts of in-domain data. In order to support the KIT lecture translation project in its effort to introduce speech translation technology in KIT’s lecture halls, we have collected a corpus of German lectures at KIT. In this paper we describe how we recorded the lectures and how we annotated them. We further give detailed statistics on the types of lectures in the corpus and its size. We collected the corpus with the purpose in mind that it should not just be suited for training a spoken language translation system the traditional way, but should also enable us to research techniques that enable the translation system to automatically and autonomously adapt itself to the varying topics and speakers of lectures</abstract>
<identifier type="citekey">stuker-etal-2012-kit</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1121_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3409</start>
<end>3414</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The KIT Lecture Corpus for Speech Translation
%A Stüker, Sebastian
%A Kraft, Florian
%A Mohr, Christian
%A Herrmann, Teresa
%A Cho, Eunah
%A Waibel, Alex
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F stuker-etal-2012-kit
%X Academic lectures offer valuable content, but often do not reach their full potential audience due to the language barrier. Human translations of lectures are too expensive to be widely used. Speech translation technology can be an affordable alternative in this case. State-of-the-art speech translation systems utilize statistical models that need to be trained on large amounts of in-domain data. In order to support the KIT lecture translation project in its effort to introduce speech translation technology in KIT’s lecture halls, we have collected a corpus of German lectures at KIT. In this paper we describe how we recorded the lectures and how we annotated them. We further give detailed statistics on the types of lectures in the corpus and its size. We collected the corpus with the purpose in mind that it should not just be suited for training a spoken language translation system the traditional way, but should also enable us to research techniques that enable the translation system to automatically and autonomously adapt itself to the varying topics and speakers of lectures
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1121_Paper.pdf
%P 3409-3414
Markdown (Informal)
[The KIT Lecture Corpus for Speech Translation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1121_Paper.pdf) (Stüker et al., LREC 2012)
ACL
- Sebastian Stüker, Florian Kraft, Christian Mohr, Teresa Herrmann, Eunah Cho, and Alex Waibel. 2012. The KIT Lecture Corpus for Speech Translation. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3409–3414, Istanbul, Turkey. European Language Resources Association (ELRA).