@inproceedings{rodriguez-fuentes-etal-2012-kalaka,
title = "{KALAKA}-2: a {TV} Broadcast Speech Database for the Recognition of {I}berian Languages in Clean and Noisy Environments",
author = "Rodr{\'\i}guez-Fuentes, Luis Javier and
Penagarikano, Mikel and
Varona, Amparo and
Diez, Mireia and
Bordel, Germ{\'a}n",
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/486_Paper.pdf",
pages = "99--105",
abstract = "This paper presents the main features (design issues, recording setup, etc.) of KALAKA-2, a TV broadcast speech database specifically designed for the development and evaluation of language recognition systems in clean and noisy environments. KALAKA-2 was created to support the Albayzin 2010 Language Recognition Evaluation (LRE), organized by the Spanish Network on Speech Technologies from June to November 2010. The database features 6 target languages: Basque, Catalan, English, Galician, Portuguese and Spanish, and includes segments in other (Out-Of-Set) languages, which allow to perform open-set verification tests. The best performance attained in the Albayzin 2010 LRE is presented and briefly discussed. The performance of a state-of-the-art system in various tasks defined on the database is also presented. In both cases, results highlight the suitability of KALAKA-2 as a benchmark for the development and evaluation of language recognition technology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-fuentes-etal-2012-kalaka">
<titleInfo>
<title>KALAKA-2: a TV Broadcast Speech Database for the Recognition of Iberian Languages in Clean and Noisy Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Javier</namePart>
<namePart type="family">Rodríguez-Fuentes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Penagarikano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amparo</namePart>
<namePart type="family">Varona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mireia</namePart>
<namePart type="family">Diez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Germán</namePart>
<namePart type="family">Bordel</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>This paper presents the main features (design issues, recording setup, etc.) of KALAKA-2, a TV broadcast speech database specifically designed for the development and evaluation of language recognition systems in clean and noisy environments. KALAKA-2 was created to support the Albayzin 2010 Language Recognition Evaluation (LRE), organized by the Spanish Network on Speech Technologies from June to November 2010. The database features 6 target languages: Basque, Catalan, English, Galician, Portuguese and Spanish, and includes segments in other (Out-Of-Set) languages, which allow to perform open-set verification tests. The best performance attained in the Albayzin 2010 LRE is presented and briefly discussed. The performance of a state-of-the-art system in various tasks defined on the database is also presented. In both cases, results highlight the suitability of KALAKA-2 as a benchmark for the development and evaluation of language recognition technology.</abstract>
<identifier type="citekey">rodriguez-fuentes-etal-2012-kalaka</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/486_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>99</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KALAKA-2: a TV Broadcast Speech Database for the Recognition of Iberian Languages in Clean and Noisy Environments
%A Rodríguez-Fuentes, Luis Javier
%A Penagarikano, Mikel
%A Varona, Amparo
%A Diez, Mireia
%A Bordel, Germán
%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 rodriguez-fuentes-etal-2012-kalaka
%X This paper presents the main features (design issues, recording setup, etc.) of KALAKA-2, a TV broadcast speech database specifically designed for the development and evaluation of language recognition systems in clean and noisy environments. KALAKA-2 was created to support the Albayzin 2010 Language Recognition Evaluation (LRE), organized by the Spanish Network on Speech Technologies from June to November 2010. The database features 6 target languages: Basque, Catalan, English, Galician, Portuguese and Spanish, and includes segments in other (Out-Of-Set) languages, which allow to perform open-set verification tests. The best performance attained in the Albayzin 2010 LRE is presented and briefly discussed. The performance of a state-of-the-art system in various tasks defined on the database is also presented. In both cases, results highlight the suitability of KALAKA-2 as a benchmark for the development and evaluation of language recognition technology.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/486_Paper.pdf
%P 99-105
Markdown (Informal)
[KALAKA-2: a TV Broadcast Speech Database for the Recognition of Iberian Languages in Clean and Noisy Environments](http://www.lrec-conf.org/proceedings/lrec2012/pdf/486_Paper.pdf) (Rodríguez-Fuentes et al., LREC 2012)
ACL