@inproceedings{odriozola-etal-2012-using,
title = "Using an {ASR} database to design a pronunciation evaluation system in {B}asque",
author = "Odriozola, Igor and
Navas, Eva and
Hernaez, Inma and
Sainz, I{\~n}aki and
Saratxaga, Ibon and
S{\'a}nchez, Jon and
Erro, Daniel",
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/822_Paper.pdf",
pages = "4122--4126",
abstract = "This paper presents a method to build CAPT systems for under resourced languages, as Basque, using a general purpose ASR speech database. More precisely, the proposed method consists in automatically determine the threshold of GOP (Goodness Of Pronunciation) scores, which have been used as pronunciation scores in phone-level. Two score distributions have been obtained for each phoneme corresponding to its correct and incorrect pronunciations. The distribution of the scores for erroneous pronunciation has been calculated inserting controlled errors in the dictionary, so that each changed phoneme has been randomly replaced by a phoneme from the same group. These groups have been obtained by means of a phonetic clustering performed using regression trees. After obtaining both distributions, the EER (Equal Error Rate) of each distribution pair has been calculated and used as a decision threshold for each phoneme. The results show that this method is useful when there is no database specifically designed for CAPT systems, although it is not as accurate as those specifically designed for this purpose.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="odriozola-etal-2012-using">
<titleInfo>
<title>Using an ASR database to design a pronunciation evaluation system in Basque</title>
</titleInfo>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Odriozola</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">Inma</namePart>
<namePart type="family">Hernaez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">Sainz</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>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Sánchez</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>
<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 presents a method to build CAPT systems for under resourced languages, as Basque, using a general purpose ASR speech database. More precisely, the proposed method consists in automatically determine the threshold of GOP (Goodness Of Pronunciation) scores, which have been used as pronunciation scores in phone-level. Two score distributions have been obtained for each phoneme corresponding to its correct and incorrect pronunciations. The distribution of the scores for erroneous pronunciation has been calculated inserting controlled errors in the dictionary, so that each changed phoneme has been randomly replaced by a phoneme from the same group. These groups have been obtained by means of a phonetic clustering performed using regression trees. After obtaining both distributions, the EER (Equal Error Rate) of each distribution pair has been calculated and used as a decision threshold for each phoneme. The results show that this method is useful when there is no database specifically designed for CAPT systems, although it is not as accurate as those specifically designed for this purpose.</abstract>
<identifier type="citekey">odriozola-etal-2012-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/822_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>4122</start>
<end>4126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using an ASR database to design a pronunciation evaluation system in Basque
%A Odriozola, Igor
%A Navas, Eva
%A Hernaez, Inma
%A Sainz, Iñaki
%A Saratxaga, Ibon
%A Sánchez, Jon
%A Erro, Daniel
%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 odriozola-etal-2012-using
%X This paper presents a method to build CAPT systems for under resourced languages, as Basque, using a general purpose ASR speech database. More precisely, the proposed method consists in automatically determine the threshold of GOP (Goodness Of Pronunciation) scores, which have been used as pronunciation scores in phone-level. Two score distributions have been obtained for each phoneme corresponding to its correct and incorrect pronunciations. The distribution of the scores for erroneous pronunciation has been calculated inserting controlled errors in the dictionary, so that each changed phoneme has been randomly replaced by a phoneme from the same group. These groups have been obtained by means of a phonetic clustering performed using regression trees. After obtaining both distributions, the EER (Equal Error Rate) of each distribution pair has been calculated and used as a decision threshold for each phoneme. The results show that this method is useful when there is no database specifically designed for CAPT systems, although it is not as accurate as those specifically designed for this purpose.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/822_Paper.pdf
%P 4122-4126
Markdown (Informal)
[Using an ASR database to design a pronunciation evaluation system in Basque](http://www.lrec-conf.org/proceedings/lrec2012/pdf/822_Paper.pdf) (Odriozola et al., LREC 2012)
ACL