@inproceedings{valkova-etal-2012-balanced,
title = "Balanced data repository of spontaneous spoken {C}zech",
author = "V{\'a}lkov{\'a}, Lucie and
Waclawi{\v{c}}ov{\'a}, Martina and
K{\v{r}}en, Michal",
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/179_Paper.pdf",
pages = "3345--3349",
abstract = "The paper presents data repository that will be used as a source of data for ORAL2013, a new corpus of spontaneous spoken Czech. The corpus is planned to be published in 2013 within the framework of the Czech National Corpus and it will contain both the audio recordings and their transcriptions manually aligned with time stamps. The corpus will be designed as a representation of contemporary spontaneous spoken language used in informal, real-life situations on the area of the whole Czech Republic and thus balanced in the main sociolinguistic categories of speakers. Therefore, the data repository features broad regional coverage with large variety of speakers, as well as precise and uniform processing. The repository is already built, basically balanced and sized 3 million words proper (i.e. tokens not including punctuation). Before the publication, another set of overall consistency checks will be carried out, as well as final selection of the transcriptions to be included into ORAL2013 as the final product.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="valkova-etal-2012-balanced">
<titleInfo>
<title>Balanced data repository of spontaneous spoken Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Válková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="family">Waclawičová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Křen</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>The paper presents data repository that will be used as a source of data for ORAL2013, a new corpus of spontaneous spoken Czech. The corpus is planned to be published in 2013 within the framework of the Czech National Corpus and it will contain both the audio recordings and their transcriptions manually aligned with time stamps. The corpus will be designed as a representation of contemporary spontaneous spoken language used in informal, real-life situations on the area of the whole Czech Republic and thus balanced in the main sociolinguistic categories of speakers. Therefore, the data repository features broad regional coverage with large variety of speakers, as well as precise and uniform processing. The repository is already built, basically balanced and sized 3 million words proper (i.e. tokens not including punctuation). Before the publication, another set of overall consistency checks will be carried out, as well as final selection of the transcriptions to be included into ORAL2013 as the final product.</abstract>
<identifier type="citekey">valkova-etal-2012-balanced</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/179_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3345</start>
<end>3349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balanced data repository of spontaneous spoken Czech
%A Válková, Lucie
%A Waclawičová, Martina
%A Křen, Michal
%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 valkova-etal-2012-balanced
%X The paper presents data repository that will be used as a source of data for ORAL2013, a new corpus of spontaneous spoken Czech. The corpus is planned to be published in 2013 within the framework of the Czech National Corpus and it will contain both the audio recordings and their transcriptions manually aligned with time stamps. The corpus will be designed as a representation of contemporary spontaneous spoken language used in informal, real-life situations on the area of the whole Czech Republic and thus balanced in the main sociolinguistic categories of speakers. Therefore, the data repository features broad regional coverage with large variety of speakers, as well as precise and uniform processing. The repository is already built, basically balanced and sized 3 million words proper (i.e. tokens not including punctuation). Before the publication, another set of overall consistency checks will be carried out, as well as final selection of the transcriptions to be included into ORAL2013 as the final product.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/179_Paper.pdf
%P 3345-3349
Markdown (Informal)
[Balanced data repository of spontaneous spoken Czech](http://www.lrec-conf.org/proceedings/lrec2012/pdf/179_Paper.pdf) (Válková et al., LREC 2012)
ACL
- Lucie Válková, Martina Waclawičová, and Michal Křen. 2012. Balanced data repository of spontaneous spoken Czech. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3345–3349, Istanbul, Turkey. European Language Resources Association (ELRA).