@inproceedings{bendahman-etal-2008-quick,
title = "Quick Rich Transcriptions of {A}rabic Broadcast News Speech Data",
author = "Bendahman, Chomicha and
Glenn, Meghan and
Mostefa, Djamel and
Paulsson, Niklas and
Strassel, Stephanie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/915_paper.pdf",
abstract = "This paper describes the collect and transcription of a large set of Arabic broadcast news speech data. A total of more than 2000 hours of data was transcribed. The transcription factor for transcribing the broadcast news data has been reduced using a method such as Quick Rich Transcription (QRTR) as well as reducing the number of quality controls performed on the data. The data was collected from several Arabic TV and radio sources and from both Modern Standard Arabic and dialectal Arabic. The orthographic transcriptions included segmentation, speaker turns, topics, sentence unit types and a minimal noise mark-up. The transcripts were produced as a part of the GALE project.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bendahman-etal-2008-quick">
<titleInfo>
<title>Quick Rich Transcriptions of Arabic Broadcast News Speech Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chomicha</namePart>
<namePart type="family">Bendahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghan</namePart>
<namePart type="family">Glenn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamel</namePart>
<namePart type="family">Mostefa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Paulsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the collect and transcription of a large set of Arabic broadcast news speech data. A total of more than 2000 hours of data was transcribed. The transcription factor for transcribing the broadcast news data has been reduced using a method such as Quick Rich Transcription (QRTR) as well as reducing the number of quality controls performed on the data. The data was collected from several Arabic TV and radio sources and from both Modern Standard Arabic and dialectal Arabic. The orthographic transcriptions included segmentation, speaker turns, topics, sentence unit types and a minimal noise mark-up. The transcripts were produced as a part of the GALE project.</abstract>
<identifier type="citekey">bendahman-etal-2008-quick</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/915_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quick Rich Transcriptions of Arabic Broadcast News Speech Data
%A Bendahman, Chomicha
%A Glenn, Meghan
%A Mostefa, Djamel
%A Paulsson, Niklas
%A Strassel, Stephanie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F bendahman-etal-2008-quick
%X This paper describes the collect and transcription of a large set of Arabic broadcast news speech data. A total of more than 2000 hours of data was transcribed. The transcription factor for transcribing the broadcast news data has been reduced using a method such as Quick Rich Transcription (QRTR) as well as reducing the number of quality controls performed on the data. The data was collected from several Arabic TV and radio sources and from both Modern Standard Arabic and dialectal Arabic. The orthographic transcriptions included segmentation, speaker turns, topics, sentence unit types and a minimal noise mark-up. The transcripts were produced as a part of the GALE project.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/915_paper.pdf
Markdown (Informal)
[Quick Rich Transcriptions of Arabic Broadcast News Speech Data](http://www.lrec-conf.org/proceedings/lrec2008/pdf/915_paper.pdf) (Bendahman et al., LREC 2008)
ACL
- Chomicha Bendahman, Meghan Glenn, Djamel Mostefa, Niklas Paulsson, and Stephanie Strassel. 2008. Quick Rich Transcriptions of Arabic Broadcast News Speech Data. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).