@inproceedings{merkus-schiel-2012-statistical,
title = "Statistical Evaluation of Pronunciation Encoding",
author = "Merkus, Iris and
Schiel, Florian",
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/391_Paper.pdf",
pages = "981--985",
abstract = "In this study we investigate the idea to automatically evaluate newly created pronunciation encodings for being correct or containing a potential error. Using a cascaded triphone detector and phonotactical n-gram modeling with an optimal Bayesian threshold we classify unknown pronunciation transcripts into the classes 'probably faulty' or 'probably correct'. Transcripts tagged 'probably faulty' are forwarded to a manual inspection performed by an expert, while encodings tagged 'probably correct' are passed without further inspection. An evaluation of the new method on the German PHONOLEX lexical resource shows that with a tolerable error margin of approximately 3{\%} faulty transcriptions a major reduction in work effort during the production of a new lexical resource can be achieved.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="merkus-schiel-2012-statistical">
<titleInfo>
<title>Statistical Evaluation of Pronunciation Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Merkus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Schiel</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>In this study we investigate the idea to automatically evaluate newly created pronunciation encodings for being correct or containing a potential error. Using a cascaded triphone detector and phonotactical n-gram modeling with an optimal Bayesian threshold we classify unknown pronunciation transcripts into the classes ’probably faulty’ or ’probably correct’. Transcripts tagged ’probably faulty’ are forwarded to a manual inspection performed by an expert, while encodings tagged ’probably correct’ are passed without further inspection. An evaluation of the new method on the German PHONOLEX lexical resource shows that with a tolerable error margin of approximately 3% faulty transcriptions a major reduction in work effort during the production of a new lexical resource can be achieved.</abstract>
<identifier type="citekey">merkus-schiel-2012-statistical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/391_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>981</start>
<end>985</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Evaluation of Pronunciation Encoding
%A Merkus, Iris
%A Schiel, Florian
%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 merkus-schiel-2012-statistical
%X In this study we investigate the idea to automatically evaluate newly created pronunciation encodings for being correct or containing a potential error. Using a cascaded triphone detector and phonotactical n-gram modeling with an optimal Bayesian threshold we classify unknown pronunciation transcripts into the classes ’probably faulty’ or ’probably correct’. Transcripts tagged ’probably faulty’ are forwarded to a manual inspection performed by an expert, while encodings tagged ’probably correct’ are passed without further inspection. An evaluation of the new method on the German PHONOLEX lexical resource shows that with a tolerable error margin of approximately 3% faulty transcriptions a major reduction in work effort during the production of a new lexical resource can be achieved.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/391_Paper.pdf
%P 981-985
Markdown (Informal)
[Statistical Evaluation of Pronunciation Encoding](http://www.lrec-conf.org/proceedings/lrec2012/pdf/391_Paper.pdf) (Merkus & Schiel, LREC 2012)
ACL
- Iris Merkus and Florian Schiel. 2012. Statistical Evaluation of Pronunciation Encoding. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 981–985, Istanbul, Turkey. European Language Resources Association (ELRA).