@inproceedings{campillo-etal-2010-building,
title = "Building High Quality Databases for Minority Languages such as {G}alician",
author = "Campillo, Francisco and
Braga, Daniela and
Mour{\'\i}n, Ana Bel{\'e}n and
Garc{\'\i}a-Mateo, Carmen and
Silva, Pedro and
Dias, Miguel Sales and
M{\'e}ndez, Francisco",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/790_Paper.pdf",
abstract = "This paper describes the result of a joint R{\&}D project between Microsoft Portugal and the Signal Theory Group of the University of Vigo (Spain), where a set of language resources was developed with application to Text―to―Speech synthesis. First, a large Corpus of 10000 Galician sentences was designed and recorded by a professional female speaker. Second, a lexicon with phonetic and grammatical information of over 90000 entries was collected and reviewed manually by a linguist expert. And finally, these resources were used for a MOS (Mean Opinion Score) perceptual test to compare two state―of―the―art speech synthesizers of both groups, the one from Microsoft based on HMM, and the one from the University of Vigo based on unit selection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="campillo-etal-2010-building">
<titleInfo>
<title>Building High Quality Databases for Minority Languages such as Galician</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Campillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Braga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Belén</namePart>
<namePart type="family">Mourín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="family">García-Mateo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Sales</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Méndez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the result of a joint R&D project between Microsoft Portugal and the Signal Theory Group of the University of Vigo (Spain), where a set of language resources was developed with application to Text―to―Speech synthesis. First, a large Corpus of 10000 Galician sentences was designed and recorded by a professional female speaker. Second, a lexicon with phonetic and grammatical information of over 90000 entries was collected and reviewed manually by a linguist expert. And finally, these resources were used for a MOS (Mean Opinion Score) perceptual test to compare two state―of―the―art speech synthesizers of both groups, the one from Microsoft based on HMM, and the one from the University of Vigo based on unit selection.</abstract>
<identifier type="citekey">campillo-etal-2010-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/790_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building High Quality Databases for Minority Languages such as Galician
%A Campillo, Francisco
%A Braga, Daniela
%A Mourín, Ana Belén
%A García-Mateo, Carmen
%A Silva, Pedro
%A Dias, Miguel Sales
%A Méndez, Francisco
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F campillo-etal-2010-building
%X This paper describes the result of a joint R&D project between Microsoft Portugal and the Signal Theory Group of the University of Vigo (Spain), where a set of language resources was developed with application to Text―to―Speech synthesis. First, a large Corpus of 10000 Galician sentences was designed and recorded by a professional female speaker. Second, a lexicon with phonetic and grammatical information of over 90000 entries was collected and reviewed manually by a linguist expert. And finally, these resources were used for a MOS (Mean Opinion Score) perceptual test to compare two state―of―the―art speech synthesizers of both groups, the one from Microsoft based on HMM, and the one from the University of Vigo based on unit selection.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/790_Paper.pdf
Markdown (Informal)
[Building High Quality Databases for Minority Languages such as Galician](http://www.lrec-conf.org/proceedings/lrec2010/pdf/790_Paper.pdf) (Campillo et al., LREC 2010)
ACL
- Francisco Campillo, Daniela Braga, Ana Belén Mourín, Carmen García-Mateo, Pedro Silva, Miguel Sales Dias, and Francisco Méndez. 2010. Building High Quality Databases for Minority Languages such as Galician. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).