@inproceedings{umbert-etal-2006-spanish,
title = "{S}panish Synthesis Corpora",
author = {Umbert, Mart{\'\i} and
Moreno, Asunci{\'o}n and
Ag{\"u}ero, Pablo and
Bonafonte, Antonio},
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/590_pdf.pdf",
abstract = "This paper deals with the design of a synthesis database for a high quality corpus-based Speech Synthesis system in Spanish. The database has been designed for speech synthesis, speech conversion and expressive speech. The design follows the specifications of TC-STAR project and has been applied to collect equivalent English and Mandarin synthesis databases. The sentences of the corpus have been selected mainly from transcribed speech and novels. The selection criterion is a phonetic and prosodic coverage. The corpus was completed with sentences specifically designed to cover frequent phrases and words. Two baseline speakers and four bilingual speakers were recorded. Recordings consist of 10 hours of speech for each baseline speaker and one hour of speech for each voice conversion bilingual speaker. The database is labelled and segmented. Pitch marks and phonetic segmentation was done automatically and up to 50{\%} manually supervised. The database will be available at ELRA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="umbert-etal-2006-spanish">
<titleInfo>
<title>Spanish Synthesis Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martí</namePart>
<namePart type="family">Umbert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asunción</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Agüero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Bonafonte</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>This paper deals with the design of a synthesis database for a high quality corpus-based Speech Synthesis system in Spanish. The database has been designed for speech synthesis, speech conversion and expressive speech. The design follows the specifications of TC-STAR project and has been applied to collect equivalent English and Mandarin synthesis databases. The sentences of the corpus have been selected mainly from transcribed speech and novels. The selection criterion is a phonetic and prosodic coverage. The corpus was completed with sentences specifically designed to cover frequent phrases and words. Two baseline speakers and four bilingual speakers were recorded. Recordings consist of 10 hours of speech for each baseline speaker and one hour of speech for each voice conversion bilingual speaker. The database is labelled and segmented. Pitch marks and phonetic segmentation was done automatically and up to 50% manually supervised. The database will be available at ELRA.</abstract>
<identifier type="citekey">umbert-etal-2006-spanish</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/590_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spanish Synthesis Corpora
%A Umbert, Martí
%A Moreno, Asunción
%A Agüero, Pablo
%A Bonafonte, Antonio
%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 umbert-etal-2006-spanish
%X This paper deals with the design of a synthesis database for a high quality corpus-based Speech Synthesis system in Spanish. The database has been designed for speech synthesis, speech conversion and expressive speech. The design follows the specifications of TC-STAR project and has been applied to collect equivalent English and Mandarin synthesis databases. The sentences of the corpus have been selected mainly from transcribed speech and novels. The selection criterion is a phonetic and prosodic coverage. The corpus was completed with sentences specifically designed to cover frequent phrases and words. Two baseline speakers and four bilingual speakers were recorded. Recordings consist of 10 hours of speech for each baseline speaker and one hour of speech for each voice conversion bilingual speaker. The database is labelled and segmented. Pitch marks and phonetic segmentation was done automatically and up to 50% manually supervised. The database will be available at ELRA.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/590_pdf.pdf
Markdown (Informal)
[Spanish Synthesis Corpora](http://www.lrec-conf.org/proceedings/lrec2006/pdf/590_pdf.pdf) (Umbert et al., LREC 2006)
ACL
- Martí Umbert, Asunción Moreno, Pablo Agüero, and Antonio Bonafonte. 2006. Spanish Synthesis Corpora. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).