@inproceedings{tavarez-etal-2012-strategies,
title = "Strategies to Improve a Speaker Diarisation Tool",
author = "Tavarez, David and
Navas, Eva and
Erro, Daniel and
Saratxaga, Ibon",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf",
pages = "4117--4121",
abstract = "This paper describes the different strategies used to improve the results obtained by an off-line speaker diarisation tool with the Albayzin 2010 diarisation database. The errors made by the system have been analyzed and different strategies have been proposed to reduce each kind of error. Very short segments incorrectly labelled and different appearances of one speaker labelled with different identifiers are the most common errors. A post-processing module that refines the segmentation by retraining the GMM models of the speakers involved has been built to cope with these errors. This post-processing module has been tuned with the training dataset and improves the result of the diarisation system by 16.4{\%} in the test dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tavarez-etal-2012-strategies">
<titleInfo>
<title>Strategies to Improve a Speaker Diarisation Tool</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>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the different strategies used to improve the results obtained by an off-line speaker diarisation tool with the Albayzin 2010 diarisation database. The errors made by the system have been analyzed and different strategies have been proposed to reduce each kind of error. Very short segments incorrectly labelled and different appearances of one speaker labelled with different identifiers are the most common errors. A post-processing module that refines the segmentation by retraining the GMM models of the speakers involved has been built to cope with these errors. This post-processing module has been tuned with the training dataset and improves the result of the diarisation system by 16.4% in the test dataset.</abstract>
<identifier type="citekey">tavarez-etal-2012-strategies</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>4117</start>
<end>4121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Strategies to Improve a Speaker Diarisation Tool
%A Tavarez, David
%A Navas, Eva
%A Erro, Daniel
%A Saratxaga, Ibon
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F tavarez-etal-2012-strategies
%X This paper describes the different strategies used to improve the results obtained by an off-line speaker diarisation tool with the Albayzin 2010 diarisation database. The errors made by the system have been analyzed and different strategies have been proposed to reduce each kind of error. Very short segments incorrectly labelled and different appearances of one speaker labelled with different identifiers are the most common errors. A post-processing module that refines the segmentation by retraining the GMM models of the speakers involved has been built to cope with these errors. This post-processing module has been tuned with the training dataset and improves the result of the diarisation system by 16.4% in the test dataset.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf
%P 4117-4121
Markdown (Informal)
[Strategies to Improve a Speaker Diarisation Tool](http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf) (Tavarez et al., LREC 2012)
ACL
- David Tavarez, Eva Navas, Daniel Erro, and Ibon Saratxaga. 2012. Strategies to Improve a Speaker Diarisation Tool. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 4117–4121, Istanbul, Turkey. European Language Resources Association (ELRA).