@inproceedings{koprivova-etal-2014-mapping,
title = "Mapping Diatopic and Diachronic Variation in Spoken {C}zech: The {ORTOFON} and {DIALEKT} Corpora",
author = "Kop{\v{r}}ivov{\'a}, Marie and
Gol{\'a}{\v{n}}ov{\'a}, Hana and
Klime{\v{s}}ov{\'a}, Petra and
Luke{\v{s}}, David",
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/252_Paper.pdf",
pages = "376--382",
abstract = "ORTOFON and DIALEKT are two corpora of spoken Czech (recordings + transcripts) which are currently being built at the Institute of the Czech National Corpus. The first one (ORTOFON) continues the tradition of the CNC{'}s ORAL series of spoken corpora by focusing on collecting recordings of unscripted informal spoken interactions ({``}prototypically spoken texts{''}), but also provides new features, most notably an annotation scheme with multiple tiers per speaker, including orthographic and phonetic transcripts and allowing for a more precise treatment of overlapping speech. Rich speaker- and situation-related metadata are also collected for possible use as factors in sociolinguistic analyses. One of the stated goals is to make the data in the corpus balanced with respect to a subset of these. The second project, DIALEKT, consists in annotating (in a way partially compatible with the ORTOFON corpus) and providing electronic access to historical (1960s{--}80s) dialect recordings, mainly of a monological nature, from all over the Czech Republic. The goal is to integrate both corpora into one map-based browsing interface, allowing an intuitive and informative spatial visualization of query results or dialect feature maps, confrontation with isoglosses previously established through the effort of dialectologists etc.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koprivova-etal-2014-mapping">
<titleInfo>
<title>Mapping Diatopic and Diachronic Variation in Spoken Czech: The ORTOFON and DIALEKT Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Kopřivová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hana</namePart>
<namePart type="family">Goláňová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petra</namePart>
<namePart type="family">Klimešová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Lukeš</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>ORTOFON and DIALEKT are two corpora of spoken Czech (recordings + transcripts) which are currently being built at the Institute of the Czech National Corpus. The first one (ORTOFON) continues the tradition of the CNC’s ORAL series of spoken corpora by focusing on collecting recordings of unscripted informal spoken interactions (“prototypically spoken texts”), but also provides new features, most notably an annotation scheme with multiple tiers per speaker, including orthographic and phonetic transcripts and allowing for a more precise treatment of overlapping speech. Rich speaker- and situation-related metadata are also collected for possible use as factors in sociolinguistic analyses. One of the stated goals is to make the data in the corpus balanced with respect to a subset of these. The second project, DIALEKT, consists in annotating (in a way partially compatible with the ORTOFON corpus) and providing electronic access to historical (1960s–80s) dialect recordings, mainly of a monological nature, from all over the Czech Republic. The goal is to integrate both corpora into one map-based browsing interface, allowing an intuitive and informative spatial visualization of query results or dialect feature maps, confrontation with isoglosses previously established through the effort of dialectologists etc.</abstract>
<identifier type="citekey">koprivova-etal-2014-mapping</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/252_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>376</start>
<end>382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mapping Diatopic and Diachronic Variation in Spoken Czech: The ORTOFON and DIALEKT Corpora
%A Kopřivová, Marie
%A Goláňová, Hana
%A Klimešová, Petra
%A Lukeš, David
%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 koprivova-etal-2014-mapping
%X ORTOFON and DIALEKT are two corpora of spoken Czech (recordings + transcripts) which are currently being built at the Institute of the Czech National Corpus. The first one (ORTOFON) continues the tradition of the CNC’s ORAL series of spoken corpora by focusing on collecting recordings of unscripted informal spoken interactions (“prototypically spoken texts”), but also provides new features, most notably an annotation scheme with multiple tiers per speaker, including orthographic and phonetic transcripts and allowing for a more precise treatment of overlapping speech. Rich speaker- and situation-related metadata are also collected for possible use as factors in sociolinguistic analyses. One of the stated goals is to make the data in the corpus balanced with respect to a subset of these. The second project, DIALEKT, consists in annotating (in a way partially compatible with the ORTOFON corpus) and providing electronic access to historical (1960s–80s) dialect recordings, mainly of a monological nature, from all over the Czech Republic. The goal is to integrate both corpora into one map-based browsing interface, allowing an intuitive and informative spatial visualization of query results or dialect feature maps, confrontation with isoglosses previously established through the effort of dialectologists etc.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/252_Paper.pdf
%P 376-382
Markdown (Informal)
[Mapping Diatopic and Diachronic Variation in Spoken Czech: The ORTOFON and DIALEKT Corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/252_Paper.pdf) (Kopřivová et al., LREC 2014)
ACL