@inproceedings{cho-etal-2014-corpus,
title = "A Corpus of Spontaneous Speech in Lectures: The {KIT} Lecture Corpus for Spoken Language Processing and Translation",
author = {Cho, Eunah and
F{\"u}nfer, Sarah and
St{\"u}ker, Sebastian and
Waibel, Alex},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/311_Paper.pdf",
pages = "1554--1559",
abstract = "With the increasing number of applications handling spontaneous speech, the needs to process spoken languages become stronger. Speech disfluency is one of the most challenging tasks to deal with in automatic speech processing. As most applications are trained with well-formed, written texts, many issues arise when processing spontaneous speech due to its distinctive characteristics. Therefore, more data with annotated speech disfluencies will help the adaptation of natural language processing applications, such as machine translation systems. In order to support this, we have annotated speech disfluencies in German lectures at KIT. In this paper we describe how we annotated the disfluencies in the data and provide detailed statistics on the size of the corpus and the speakers. Moreover, machine translation performance on a source text including disfluencies is compared to the results of the translation of a source text without different sorts of disfluencies or no disfluencies at all.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2014-corpus">
<titleInfo>
<title>A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation</title>
</titleInfo>
<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">Sarah</namePart>
<namePart type="family">Fünfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the increasing number of applications handling spontaneous speech, the needs to process spoken languages become stronger. Speech disfluency is one of the most challenging tasks to deal with in automatic speech processing. As most applications are trained with well-formed, written texts, many issues arise when processing spontaneous speech due to its distinctive characteristics. Therefore, more data with annotated speech disfluencies will help the adaptation of natural language processing applications, such as machine translation systems. In order to support this, we have annotated speech disfluencies in German lectures at KIT. In this paper we describe how we annotated the disfluencies in the data and provide detailed statistics on the size of the corpus and the speakers. Moreover, machine translation performance on a source text including disfluencies is compared to the results of the translation of a source text without different sorts of disfluencies or no disfluencies at all.</abstract>
<identifier type="citekey">cho-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/311_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1554</start>
<end>1559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation
%A Cho, Eunah
%A Fünfer, Sarah
%A Stüker, Sebastian
%A Waibel, Alex
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F cho-etal-2014-corpus
%X With the increasing number of applications handling spontaneous speech, the needs to process spoken languages become stronger. Speech disfluency is one of the most challenging tasks to deal with in automatic speech processing. As most applications are trained with well-formed, written texts, many issues arise when processing spontaneous speech due to its distinctive characteristics. Therefore, more data with annotated speech disfluencies will help the adaptation of natural language processing applications, such as machine translation systems. In order to support this, we have annotated speech disfluencies in German lectures at KIT. In this paper we describe how we annotated the disfluencies in the data and provide detailed statistics on the size of the corpus and the speakers. Moreover, machine translation performance on a source text including disfluencies is compared to the results of the translation of a source text without different sorts of disfluencies or no disfluencies at all.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/311_Paper.pdf
%P 1554-1559
Markdown (Informal)
[A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/311_Paper.pdf) (Cho et al., LREC 2014)
ACL