@inproceedings{ludusan-etal-2014-bridging,
title = "Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems",
author = "Ludusan, Bogdan and
Versteegh, Maarten and
Jansen, Aren and
Gravier, Guillaume and
Cao, Xuan-Nga and
Johnson, Mark and
Dupoux, Emmanuel",
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/320_Paper.pdf",
pages = "560--567",
abstract = "The unsupervised discovery of linguistic terms from either continuous phoneme transcriptions or from raw speech has seen an increasing interest in the past years both from a theoretical and a practical standpoint. Yet, there exists no common accepted evaluation method for the systems performing term discovery. Here, we propose such an evaluation toolbox, drawing ideas from both speech technology and natural language processing. We first transform the speech-based output into a symbolic representation and compute five types of evaluation metrics on this representation: the quality of acoustic matching, the quality of the clusters found, and the quality of the alignment with real words (type, token, and boundary scores). We tested our approach on two term discovery systems taking speech as input, and one using symbolic input. The latter was run using both the gold transcription and a transcription obtained from an automatic speech recognizer, in order to simulate the case when only imperfect symbolic information is available. The results obtained are analysed through the use of the proposed evaluation metrics and the implications of these metrics are discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ludusan-etal-2014-bridging">
<titleInfo>
<title>Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Ludusan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">Versteegh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aren</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Nga</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Dupoux</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 unsupervised discovery of linguistic terms from either continuous phoneme transcriptions or from raw speech has seen an increasing interest in the past years both from a theoretical and a practical standpoint. Yet, there exists no common accepted evaluation method for the systems performing term discovery. Here, we propose such an evaluation toolbox, drawing ideas from both speech technology and natural language processing. We first transform the speech-based output into a symbolic representation and compute five types of evaluation metrics on this representation: the quality of acoustic matching, the quality of the clusters found, and the quality of the alignment with real words (type, token, and boundary scores). We tested our approach on two term discovery systems taking speech as input, and one using symbolic input. The latter was run using both the gold transcription and a transcription obtained from an automatic speech recognizer, in order to simulate the case when only imperfect symbolic information is available. The results obtained are analysed through the use of the proposed evaluation metrics and the implications of these metrics are discussed.</abstract>
<identifier type="citekey">ludusan-etal-2014-bridging</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/320_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>560</start>
<end>567</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems
%A Ludusan, Bogdan
%A Versteegh, Maarten
%A Jansen, Aren
%A Gravier, Guillaume
%A Cao, Xuan-Nga
%A Johnson, Mark
%A Dupoux, Emmanuel
%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 ludusan-etal-2014-bridging
%X The unsupervised discovery of linguistic terms from either continuous phoneme transcriptions or from raw speech has seen an increasing interest in the past years both from a theoretical and a practical standpoint. Yet, there exists no common accepted evaluation method for the systems performing term discovery. Here, we propose such an evaluation toolbox, drawing ideas from both speech technology and natural language processing. We first transform the speech-based output into a symbolic representation and compute five types of evaluation metrics on this representation: the quality of acoustic matching, the quality of the clusters found, and the quality of the alignment with real words (type, token, and boundary scores). We tested our approach on two term discovery systems taking speech as input, and one using symbolic input. The latter was run using both the gold transcription and a transcription obtained from an automatic speech recognizer, in order to simulate the case when only imperfect symbolic information is available. The results obtained are analysed through the use of the proposed evaluation metrics and the implications of these metrics are discussed.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/320_Paper.pdf
%P 560-567
Markdown (Informal)
[Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems](http://www.lrec-conf.org/proceedings/lrec2014/pdf/320_Paper.pdf) (Ludusan et al., LREC 2014)
ACL