@inproceedings{zgank-etal-2014-slovene,
title = "The {S}lovene {BNSI} Broadcast News database and reference speech corpus {GOS}: Towards the uniform guidelines for future work",
author = "{\v{Z}}gank, Andrej and
Vitez, Ana Zwitter and
Verdonik, Darinka",
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/710_Paper.pdf",
pages = "2644--2647",
abstract = "The aim of the paper is to search for common guidelines for the future development of speech databases for less resourced languages in order to make them the most useful for both main fields of their use, linguistic research and speech technologies. We compare two standards for creating speech databases, one followed when developing the Slovene speech database for automatic speech recognition ― BNSI Broadcast News, the other followed when developing the Slovene reference speech corpus GOS, and outline possible common guidelines for future work. We also present an add-on for the GOS corpus, which enables its usage for automatic speech recognition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zgank-etal-2014-slovene">
<titleInfo>
<title>The Slovene BNSI Broadcast News database and reference speech corpus GOS: Towards the uniform guidelines for future work</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrej</namePart>
<namePart type="family">Žgank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Zwitter</namePart>
<namePart type="family">Vitez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darinka</namePart>
<namePart type="family">Verdonik</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>The aim of the paper is to search for common guidelines for the future development of speech databases for less resourced languages in order to make them the most useful for both main fields of their use, linguistic research and speech technologies. We compare two standards for creating speech databases, one followed when developing the Slovene speech database for automatic speech recognition ― BNSI Broadcast News, the other followed when developing the Slovene reference speech corpus GOS, and outline possible common guidelines for future work. We also present an add-on for the GOS corpus, which enables its usage for automatic speech recognition.</abstract>
<identifier type="citekey">zgank-etal-2014-slovene</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/710_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2644</start>
<end>2647</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Slovene BNSI Broadcast News database and reference speech corpus GOS: Towards the uniform guidelines for future work
%A Žgank, Andrej
%A Vitez, Ana Zwitter
%A Verdonik, Darinka
%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 zgank-etal-2014-slovene
%X The aim of the paper is to search for common guidelines for the future development of speech databases for less resourced languages in order to make them the most useful for both main fields of their use, linguistic research and speech technologies. We compare two standards for creating speech databases, one followed when developing the Slovene speech database for automatic speech recognition ― BNSI Broadcast News, the other followed when developing the Slovene reference speech corpus GOS, and outline possible common guidelines for future work. We also present an add-on for the GOS corpus, which enables its usage for automatic speech recognition.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/710_Paper.pdf
%P 2644-2647
Markdown (Informal)
[The Slovene BNSI Broadcast News database and reference speech corpus GOS: Towards the uniform guidelines for future work](http://www.lrec-conf.org/proceedings/lrec2014/pdf/710_Paper.pdf) (Žgank et al., LREC 2014)
ACL