@inproceedings{rodriguez-fuentes-etal-2014-kalaka,
title = "{KALAKA}-3: a database for the recognition of spoken {E}uropean languages on {Y}ou{T}ube audios",
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
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/736_Paper.pdf",
pages = "443--449",
abstract = "This paper describes the main features of KALAKA-3, a speech database specifically designed for the development and evaluation of language recognition systems. The database provides TV broadcast speech for training, and audio data extracted from YouTube videos for tuning and testing. The database was created to support the Albayzin 2012 Language Recognition Evaluation, which featured two language recognition tasks, both dealing with European languages. The first one involved six target languages (Basque, Catalan, English, Galician, Portuguese and Spanish) for which there was plenty of training data, whereas the second one involved four target languages (French, German, Greek and Italian) for which no training data was provided. Two separate sets of YouTube audio files were provided to test the performance of language recognition systems on both tasks. To allow open-set tests, these datasets included speech in 11 additional (Out-Of-Set) European languages. The paper also presents a summary of the results attained in the evaluation, along with the performance of state-of-the-art systems on the four evaluation tracks defined on the database, which demonstrates the extreme difficulty of some of them. As far as we know, this is the first database specifically designed to benchmark spoken language recognition technology on YouTube audios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-fuentes-etal-2014-kalaka">
<titleInfo>
<title>KALAKA-3: a database for the recognition of spoken European languages on YouTube audios</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>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>This paper describes the main features of KALAKA-3, a speech database specifically designed for the development and evaluation of language recognition systems. The database provides TV broadcast speech for training, and audio data extracted from YouTube videos for tuning and testing. The database was created to support the Albayzin 2012 Language Recognition Evaluation, which featured two language recognition tasks, both dealing with European languages. The first one involved six target languages (Basque, Catalan, English, Galician, Portuguese and Spanish) for which there was plenty of training data, whereas the second one involved four target languages (French, German, Greek and Italian) for which no training data was provided. Two separate sets of YouTube audio files were provided to test the performance of language recognition systems on both tasks. To allow open-set tests, these datasets included speech in 11 additional (Out-Of-Set) European languages. The paper also presents a summary of the results attained in the evaluation, along with the performance of state-of-the-art systems on the four evaluation tracks defined on the database, which demonstrates the extreme difficulty of some of them. As far as we know, this is the first database specifically designed to benchmark spoken language recognition technology on YouTube audios.</abstract>
<identifier type="citekey">rodriguez-fuentes-etal-2014-kalaka</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/736_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>443</start>
<end>449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KALAKA-3: a database for the recognition of spoken European languages on YouTube audios
%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 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 rodriguez-fuentes-etal-2014-kalaka
%X This paper describes the main features of KALAKA-3, a speech database specifically designed for the development and evaluation of language recognition systems. The database provides TV broadcast speech for training, and audio data extracted from YouTube videos for tuning and testing. The database was created to support the Albayzin 2012 Language Recognition Evaluation, which featured two language recognition tasks, both dealing with European languages. The first one involved six target languages (Basque, Catalan, English, Galician, Portuguese and Spanish) for which there was plenty of training data, whereas the second one involved four target languages (French, German, Greek and Italian) for which no training data was provided. Two separate sets of YouTube audio files were provided to test the performance of language recognition systems on both tasks. To allow open-set tests, these datasets included speech in 11 additional (Out-Of-Set) European languages. The paper also presents a summary of the results attained in the evaluation, along with the performance of state-of-the-art systems on the four evaluation tracks defined on the database, which demonstrates the extreme difficulty of some of them. As far as we know, this is the first database specifically designed to benchmark spoken language recognition technology on YouTube audios.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/736_Paper.pdf
%P 443-449
Markdown (Informal)
[KALAKA-3: a database for the recognition of spoken European languages on YouTube audios](http://www.lrec-conf.org/proceedings/lrec2014/pdf/736_Paper.pdf) (Rodríguez-Fuentes et al., LREC 2014)
ACL