@inproceedings{tavarez-etal-2014-new,
title = "New bilingual speech databases for audio diarization",
author = "Tavarez, David and
Navas, Eva and
Erro, Daniel and
Saratxaga, Ibon and
Hernaez, Inma",
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/799_Paper.pdf",
pages = "2666--2670",
abstract = "This paper describes the process of collecting and recording two new bilingual speech databases in Spanish and Basque. They are designed primarily for speaker diarization in two different application domains: broadcast news audio and recorded meetings. First, both databases have been manually segmented. Next, several diarization experiments have been carried out in order to evaluate them. Our baseline speaker diarization system has been applied to both databases with around 30{\%} of DER for broadcast news audio and 40{\%} of DER for recorded meetings. Also, the behavior of the system when different languages are used by the same speaker has been tested.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tavarez-etal-2014-new">
<titleInfo>
<title>New bilingual speech databases for audio diarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Tavarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Navas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Erro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibon</namePart>
<namePart type="family">Saratxaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inma</namePart>
<namePart type="family">Hernaez</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 process of collecting and recording two new bilingual speech databases in Spanish and Basque. They are designed primarily for speaker diarization in two different application domains: broadcast news audio and recorded meetings. First, both databases have been manually segmented. Next, several diarization experiments have been carried out in order to evaluate them. Our baseline speaker diarization system has been applied to both databases with around 30% of DER for broadcast news audio and 40% of DER for recorded meetings. Also, the behavior of the system when different languages are used by the same speaker has been tested.</abstract>
<identifier type="citekey">tavarez-etal-2014-new</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/799_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2666</start>
<end>2670</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New bilingual speech databases for audio diarization
%A Tavarez, David
%A Navas, Eva
%A Erro, Daniel
%A Saratxaga, Ibon
%A Hernaez, Inma
%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 tavarez-etal-2014-new
%X This paper describes the process of collecting and recording two new bilingual speech databases in Spanish and Basque. They are designed primarily for speaker diarization in two different application domains: broadcast news audio and recorded meetings. First, both databases have been manually segmented. Next, several diarization experiments have been carried out in order to evaluate them. Our baseline speaker diarization system has been applied to both databases with around 30% of DER for broadcast news audio and 40% of DER for recorded meetings. Also, the behavior of the system when different languages are used by the same speaker has been tested.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/799_Paper.pdf
%P 2666-2670
Markdown (Informal)
[New bilingual speech databases for audio diarization](http://www.lrec-conf.org/proceedings/lrec2014/pdf/799_Paper.pdf) (Tavarez et al., LREC 2014)
ACL
- David Tavarez, Eva Navas, Daniel Erro, Ibon Saratxaga, and Inma Hernaez. 2014. New bilingual speech databases for audio diarization. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2666–2670, Reykjavik, Iceland. European Language Resources Association (ELRA).