@inproceedings{yang-etal-2006-development,
title = "Development of a phoneme-to-phoneme (p2p) converter to improve the grapheme-to-phoneme (g2p) conversion of names",
author = "Yang, Qian and
Martens, Jean-Pierre and
Konings, Nanneke and
van den Heuvel, Henk",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/248_pdf.pdf",
abstract = "It is acknowledged that a good phonemic transcription of proper names is imperative for the success of many modern speech-based services such as directory assistance, car navigation, etc. It is also known that state-of-the-art general-purpose grapheme-to-phoneme (g2p) converters perform rather poorly on many name categories. This paper proposes to use a g2p-p2p tandem comprising a state-of-the-art general-purpose g2p converter that produces an initial transcription and a name category specific phoneme-to-phoneme (p2p) converter that aims at correcting the mistakes made by the g2p converter. The main body of the paper describes a novel methodology for the automatic construction of the p2p converter. The methodology is implemented in a software toolbox that will be made publicly available in a form that will permit the user to design a p2p converter for an arbitrary name category. To give a proof of concept, the toolbox was used for the development of three p2p converters for first names, surnames and geographical names respectively. The obtained systems are small (few rules) and effective: significant improvements (up to 50{\%} relative) of the grapheme-to-phoneme conversion are obtained. These encouraging results call for a further development and improvement of the approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2006-development">
<titleInfo>
<title>Development of a phoneme-to-phoneme (p2p) converter to improve the grapheme-to-phoneme (g2p) conversion of names</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Pierre</namePart>
<namePart type="family">Martens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanneke</namePart>
<namePart type="family">Konings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is acknowledged that a good phonemic transcription of proper names is imperative for the success of many modern speech-based services such as directory assistance, car navigation, etc. It is also known that state-of-the-art general-purpose grapheme-to-phoneme (g2p) converters perform rather poorly on many name categories. This paper proposes to use a g2p-p2p tandem comprising a state-of-the-art general-purpose g2p converter that produces an initial transcription and a name category specific phoneme-to-phoneme (p2p) converter that aims at correcting the mistakes made by the g2p converter. The main body of the paper describes a novel methodology for the automatic construction of the p2p converter. The methodology is implemented in a software toolbox that will be made publicly available in a form that will permit the user to design a p2p converter for an arbitrary name category. To give a proof of concept, the toolbox was used for the development of three p2p converters for first names, surnames and geographical names respectively. The obtained systems are small (few rules) and effective: significant improvements (up to 50% relative) of the grapheme-to-phoneme conversion are obtained. These encouraging results call for a further development and improvement of the approach.</abstract>
<identifier type="citekey">yang-etal-2006-development</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/248_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of a phoneme-to-phoneme (p2p) converter to improve the grapheme-to-phoneme (g2p) conversion of names
%A Yang, Qian
%A Martens, Jean-Pierre
%A Konings, Nanneke
%A van den Heuvel, Henk
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F yang-etal-2006-development
%X It is acknowledged that a good phonemic transcription of proper names is imperative for the success of many modern speech-based services such as directory assistance, car navigation, etc. It is also known that state-of-the-art general-purpose grapheme-to-phoneme (g2p) converters perform rather poorly on many name categories. This paper proposes to use a g2p-p2p tandem comprising a state-of-the-art general-purpose g2p converter that produces an initial transcription and a name category specific phoneme-to-phoneme (p2p) converter that aims at correcting the mistakes made by the g2p converter. The main body of the paper describes a novel methodology for the automatic construction of the p2p converter. The methodology is implemented in a software toolbox that will be made publicly available in a form that will permit the user to design a p2p converter for an arbitrary name category. To give a proof of concept, the toolbox was used for the development of three p2p converters for first names, surnames and geographical names respectively. The obtained systems are small (few rules) and effective: significant improvements (up to 50% relative) of the grapheme-to-phoneme conversion are obtained. These encouraging results call for a further development and improvement of the approach.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/248_pdf.pdf
Markdown (Informal)
[Development of a phoneme-to-phoneme (p2p) converter to improve the grapheme-to-phoneme (g2p) conversion of names](http://www.lrec-conf.org/proceedings/lrec2006/pdf/248_pdf.pdf) (Yang et al., LREC 2006)
ACL