@inproceedings{salmon-vallet-2014-effortless,
title = "An Effortless Way To Create Large-Scale Datasets For Famous Speakers",
author = "Salmon, Fran{\c{c}}ois and
Vallet, F{\'e}licien",
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/32_Paper.pdf",
pages = "348--352",
abstract = "The creation of large-scale multimedia datasets has become a scientific matter in itself. Indeed, the fully-manual annotation of hundreds or thousands of hours of video and/or audio turns out to be practically infeasible. In this paper, we propose an extremly handy approach to automatically construct a database of famous speakers from TV broadcast news material. We then run a user experiment with a correctly designed tool that demonstrates that very reliable results can be obtained with this method. In particular, a thorough error analysis demonstrates the value of the approach and provides hints for the improvement of the quality of the dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salmon-vallet-2014-effortless">
<titleInfo>
<title>An Effortless Way To Create Large-Scale Datasets For Famous Speakers</title>
</titleInfo>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Salmon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Félicien</namePart>
<namePart type="family">Vallet</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 creation of large-scale multimedia datasets has become a scientific matter in itself. Indeed, the fully-manual annotation of hundreds or thousands of hours of video and/or audio turns out to be practically infeasible. In this paper, we propose an extremly handy approach to automatically construct a database of famous speakers from TV broadcast news material. We then run a user experiment with a correctly designed tool that demonstrates that very reliable results can be obtained with this method. In particular, a thorough error analysis demonstrates the value of the approach and provides hints for the improvement of the quality of the dataset.</abstract>
<identifier type="citekey">salmon-vallet-2014-effortless</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/32_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>348</start>
<end>352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Effortless Way To Create Large-Scale Datasets For Famous Speakers
%A Salmon, François
%A Vallet, Félicien
%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 salmon-vallet-2014-effortless
%X The creation of large-scale multimedia datasets has become a scientific matter in itself. Indeed, the fully-manual annotation of hundreds or thousands of hours of video and/or audio turns out to be practically infeasible. In this paper, we propose an extremly handy approach to automatically construct a database of famous speakers from TV broadcast news material. We then run a user experiment with a correctly designed tool that demonstrates that very reliable results can be obtained with this method. In particular, a thorough error analysis demonstrates the value of the approach and provides hints for the improvement of the quality of the dataset.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/32_Paper.pdf
%P 348-352
Markdown (Informal)
[An Effortless Way To Create Large-Scale Datasets For Famous Speakers](http://www.lrec-conf.org/proceedings/lrec2014/pdf/32_Paper.pdf) (Salmon & Vallet, LREC 2014)
ACL