@inproceedings{sainz-etal-2012-versatile,
title = "Versatile Speech Databases for High Quality Synthesis for {B}asque",
author = "Sainz, I{\~n}aki and
Erro, Daniel and
Navas, Eva and
Hern{\'a}ez, Inma and
Sanchez, Jon and
Saratxaga, Ibon and
Odriozola, Igor",
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/126_Paper.pdf",
pages = "3308--3312",
abstract = "This paper presents three new speech databases for standard Basque. They are designed primarily for corpus-based synthesis but each database has its specific purpose: 1) AhoSyn: high quality speech synthesis (recorded also in Spanish), 2) AhoSpeakers: voice conversion and 3) AhoEmo3: emotional speech synthesis. The whole corpus design and the recording process are described with detail. Once the databases were collected all the data was automatically labelled and annotated. Then, an HMM-based TTS voice was built and subjectively evaluated. The results of the evaluation are pretty satisfactory: 3.70 MOS for Basque and 3.44 for Spanish. Therefore, the evaluation assesses the quality of this new speech resource and the validity of the automated processing presented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sainz-etal-2012-versatile">
<titleInfo>
<title>Versatile Speech Databases for High Quality Synthesis for Basque</title>
</titleInfo>
<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">Daniel</namePart>
<namePart type="family">Erro</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">Hernáez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Sanchez</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">Igor</namePart>
<namePart type="family">Odriozola</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 three new speech databases for standard Basque. They are designed primarily for corpus-based synthesis but each database has its specific purpose: 1) AhoSyn: high quality speech synthesis (recorded also in Spanish), 2) AhoSpeakers: voice conversion and 3) AhoEmo3: emotional speech synthesis. The whole corpus design and the recording process are described with detail. Once the databases were collected all the data was automatically labelled and annotated. Then, an HMM-based TTS voice was built and subjectively evaluated. The results of the evaluation are pretty satisfactory: 3.70 MOS for Basque and 3.44 for Spanish. Therefore, the evaluation assesses the quality of this new speech resource and the validity of the automated processing presented.</abstract>
<identifier type="citekey">sainz-etal-2012-versatile</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/126_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3308</start>
<end>3312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Versatile Speech Databases for High Quality Synthesis for Basque
%A Sainz, Iñaki
%A Erro, Daniel
%A Navas, Eva
%A Hernáez, Inma
%A Sanchez, Jon
%A Saratxaga, Ibon
%A Odriozola, Igor
%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 sainz-etal-2012-versatile
%X This paper presents three new speech databases for standard Basque. They are designed primarily for corpus-based synthesis but each database has its specific purpose: 1) AhoSyn: high quality speech synthesis (recorded also in Spanish), 2) AhoSpeakers: voice conversion and 3) AhoEmo3: emotional speech synthesis. The whole corpus design and the recording process are described with detail. Once the databases were collected all the data was automatically labelled and annotated. Then, an HMM-based TTS voice was built and subjectively evaluated. The results of the evaluation are pretty satisfactory: 3.70 MOS for Basque and 3.44 for Spanish. Therefore, the evaluation assesses the quality of this new speech resource and the validity of the automated processing presented.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/126_Paper.pdf
%P 3308-3312
Markdown (Informal)
[Versatile Speech Databases for High Quality Synthesis for Basque](http://www.lrec-conf.org/proceedings/lrec2012/pdf/126_Paper.pdf) (Sainz et al., LREC 2012)
ACL
- Iñaki Sainz, Daniel Erro, Eva Navas, Inma Hernáez, Jon Sanchez, Ibon Saratxaga, and Igor Odriozola. 2012. Versatile Speech Databases for High Quality Synthesis for Basque. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3308–3312, Istanbul, Turkey. European Language Resources Association (ELRA).