@inproceedings{kurtic-etal-2012-corpus,
title = "A Corpus of Spontaneous Multi-party Conversation in {B}osnian {S}erbo-{C}roatian and {B}ritish {E}nglish",
author = "Kurti{\'c}, Emina and
Wells, Bill and
Brown, Guy J. and
Kempton, Timothy and
Aker, Ahmet",
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/513_Paper.pdf",
pages = "1323--1327",
abstract = "In this paper we present a corpus of audio and video recordings of spontaneous, face-to-face multi-party conversation in two languages. Freely available high quality recordings of mundane, non-institutional, multi-party talk are still sparse, and this corpus aims to contribute valuable data suitable for study of multiple aspects of spoken interaction. In particular, it constitutes a unique resource for spoken Bosnian Serbo-Croatian (BSC), an under-resourced language with no spoken resources available at present. The corpus consists of just over 3 hours of free conversation in each of the target languages, BSC and British English (BE). The audio recordings have been made on separate channels using head-set microphones, as well as using a microphone array, containing 8 omni-directional microphones. The data has been segmented and transcribed using segmentation notions and transcription conventions developed from those of the conversation analysis research tradition. Furthermore, the transcriptions have been automatically aligned with the audio at the word and phone level, using the method of forced alignment. In this paper we describe the procedures behind the corpus creation and present the main features of the corpus for the study of conversation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurtic-etal-2012-corpus">
<titleInfo>
<title>A Corpus of Spontaneous Multi-party Conversation in Bosnian Serbo-Croatian and British English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emina</namePart>
<namePart type="family">Kurtić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">Wells</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Kempton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Aker</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>In this paper we present a corpus of audio and video recordings of spontaneous, face-to-face multi-party conversation in two languages. Freely available high quality recordings of mundane, non-institutional, multi-party talk are still sparse, and this corpus aims to contribute valuable data suitable for study of multiple aspects of spoken interaction. In particular, it constitutes a unique resource for spoken Bosnian Serbo-Croatian (BSC), an under-resourced language with no spoken resources available at present. The corpus consists of just over 3 hours of free conversation in each of the target languages, BSC and British English (BE). The audio recordings have been made on separate channels using head-set microphones, as well as using a microphone array, containing 8 omni-directional microphones. The data has been segmented and transcribed using segmentation notions and transcription conventions developed from those of the conversation analysis research tradition. Furthermore, the transcriptions have been automatically aligned with the audio at the word and phone level, using the method of forced alignment. In this paper we describe the procedures behind the corpus creation and present the main features of the corpus for the study of conversation.</abstract>
<identifier type="citekey">kurtic-etal-2012-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/513_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1323</start>
<end>1327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Spontaneous Multi-party Conversation in Bosnian Serbo-Croatian and British English
%A Kurtić, Emina
%A Wells, Bill
%A Brown, Guy J.
%A Kempton, Timothy
%A Aker, Ahmet
%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 kurtic-etal-2012-corpus
%X In this paper we present a corpus of audio and video recordings of spontaneous, face-to-face multi-party conversation in two languages. Freely available high quality recordings of mundane, non-institutional, multi-party talk are still sparse, and this corpus aims to contribute valuable data suitable for study of multiple aspects of spoken interaction. In particular, it constitutes a unique resource for spoken Bosnian Serbo-Croatian (BSC), an under-resourced language with no spoken resources available at present. The corpus consists of just over 3 hours of free conversation in each of the target languages, BSC and British English (BE). The audio recordings have been made on separate channels using head-set microphones, as well as using a microphone array, containing 8 omni-directional microphones. The data has been segmented and transcribed using segmentation notions and transcription conventions developed from those of the conversation analysis research tradition. Furthermore, the transcriptions have been automatically aligned with the audio at the word and phone level, using the method of forced alignment. In this paper we describe the procedures behind the corpus creation and present the main features of the corpus for the study of conversation.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/513_Paper.pdf
%P 1323-1327
Markdown (Informal)
[A Corpus of Spontaneous Multi-party Conversation in Bosnian Serbo-Croatian and British English](http://www.lrec-conf.org/proceedings/lrec2012/pdf/513_Paper.pdf) (Kurtić et al., LREC 2012)
ACL