@inproceedings{rodriguez-fuentes-etal-2010-kalaka,
title = "{KALAKA}: A {TV} Broadcast Speech Database for the Evaluation of Language Recognition Systems",
author = "Rodr{\'\i}guez-Fuentes, Luis Javier and
Penagarikano, Mikel and
Bordel, Germ{\'a}n and
Varona, Amparo and
D{\'\i}ez, Mireia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/394_Paper.pdf",
abstract = "A speech database, named KALAKA, was created to support the Albayzin 2008 Evaluation of Language Recognition Systems, organized by the Spanish Network on Speech Technologies from May to November 2008. This evaluation, designed according to the criteria and methodology applied in the NIST Language Recognition Evaluations, involved four target languages: Basque, Catalan, Galician and Spanish (official languages in Spain), and included speech signals in other (unknown) languages to allow open-set verification trials. In this paper, the process of designing, collecting data and building the train, development and evaluation datasets of KALAKA is described. Results attained in the Albayzin 2008 LRE are presented as a means of evaluating the database. The performance of a state-of-the-art language recognition system on a closed-set evaluation task is also presented for reference. Future work includes extending KALAKA by adding Portuguese and English as target languages and renewing the set of unknown languages needed to carry out open-set evaluations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-fuentes-etal-2010-kalaka">
<titleInfo>
<title>KALAKA: A TV Broadcast Speech Database for the Evaluation of Language Recognition Systems</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">Germán</namePart>
<namePart type="family">Bordel</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">Díez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A speech database, named KALAKA, was created to support the Albayzin 2008 Evaluation of Language Recognition Systems, organized by the Spanish Network on Speech Technologies from May to November 2008. This evaluation, designed according to the criteria and methodology applied in the NIST Language Recognition Evaluations, involved four target languages: Basque, Catalan, Galician and Spanish (official languages in Spain), and included speech signals in other (unknown) languages to allow open-set verification trials. In this paper, the process of designing, collecting data and building the train, development and evaluation datasets of KALAKA is described. Results attained in the Albayzin 2008 LRE are presented as a means of evaluating the database. The performance of a state-of-the-art language recognition system on a closed-set evaluation task is also presented for reference. Future work includes extending KALAKA by adding Portuguese and English as target languages and renewing the set of unknown languages needed to carry out open-set evaluations.</abstract>
<identifier type="citekey">rodriguez-fuentes-etal-2010-kalaka</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/394_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KALAKA: A TV Broadcast Speech Database for the Evaluation of Language Recognition Systems
%A Rodríguez-Fuentes, Luis Javier
%A Penagarikano, Mikel
%A Bordel, Germán
%A Varona, Amparo
%A Díez, Mireia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F rodriguez-fuentes-etal-2010-kalaka
%X A speech database, named KALAKA, was created to support the Albayzin 2008 Evaluation of Language Recognition Systems, organized by the Spanish Network on Speech Technologies from May to November 2008. This evaluation, designed according to the criteria and methodology applied in the NIST Language Recognition Evaluations, involved four target languages: Basque, Catalan, Galician and Spanish (official languages in Spain), and included speech signals in other (unknown) languages to allow open-set verification trials. In this paper, the process of designing, collecting data and building the train, development and evaluation datasets of KALAKA is described. Results attained in the Albayzin 2008 LRE are presented as a means of evaluating the database. The performance of a state-of-the-art language recognition system on a closed-set evaluation task is also presented for reference. Future work includes extending KALAKA by adding Portuguese and English as target languages and renewing the set of unknown languages needed to carry out open-set evaluations.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/394_Paper.pdf
Markdown (Informal)
[KALAKA: A TV Broadcast Speech Database for the Evaluation of Language Recognition Systems](http://www.lrec-conf.org/proceedings/lrec2010/pdf/394_Paper.pdf) (Rodríguez-Fuentes et al., LREC 2010)
ACL