@inproceedings{oliveira-etal-2008-methodologies,
title = "Methodologies for Designing and Recording Speech Databases for Corpus Based Synthesis",
author = "Oliveira, Lu{\'\i}s and
Paulo, S{\'e}rgio and
Figueira, Lu{\'\i}s and
Mendes, Carlos and
Nunes, Ana and
Godinho, Joaquim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/741_paper.pdf",
abstract = "In this paper we share our experience and describe the methodologies that we have used in designing and recording large speech databases for applications requiring speech synthesis. Given the growing demand for customized and domain specific voices for use in corpus based synthesis systems, we believe that good practices should be established for the creation of these databases which are a key factor in the quality of the resulting speech synthesizer. We will focus on the designing of the recording prompts, on the speaker selection procedure, on the recording setup and on the quality control of the resulting database. One of the major challenges was to assure the uniformity of the recordings during the 20 two-hour recording sessions that each speaker had to perform, to produce a total of 13 hours of recorded speech for each of the four speakers. This work was conducted in the scope of the Tecnovoz project that brought together 4 speech research centers and 9 companies with the goal of integrating speech technologies in a wide range of applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oliveira-etal-2008-methodologies">
<titleInfo>
<title>Methodologies for Designing and Recording Speech Databases for Corpus Based Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sérgio</namePart>
<namePart type="family">Paulo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Figueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Mendes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joaquim</namePart>
<namePart type="family">Godinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we share our experience and describe the methodologies that we have used in designing and recording large speech databases for applications requiring speech synthesis. Given the growing demand for customized and domain specific voices for use in corpus based synthesis systems, we believe that good practices should be established for the creation of these databases which are a key factor in the quality of the resulting speech synthesizer. We will focus on the designing of the recording prompts, on the speaker selection procedure, on the recording setup and on the quality control of the resulting database. One of the major challenges was to assure the uniformity of the recordings during the 20 two-hour recording sessions that each speaker had to perform, to produce a total of 13 hours of recorded speech for each of the four speakers. This work was conducted in the scope of the Tecnovoz project that brought together 4 speech research centers and 9 companies with the goal of integrating speech technologies in a wide range of applications.</abstract>
<identifier type="citekey">oliveira-etal-2008-methodologies</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/741_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Methodologies for Designing and Recording Speech Databases for Corpus Based Synthesis
%A Oliveira, Luís
%A Paulo, Sérgio
%A Figueira, Luís
%A Mendes, Carlos
%A Nunes, Ana
%A Godinho, Joaquim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F oliveira-etal-2008-methodologies
%X In this paper we share our experience and describe the methodologies that we have used in designing and recording large speech databases for applications requiring speech synthesis. Given the growing demand for customized and domain specific voices for use in corpus based synthesis systems, we believe that good practices should be established for the creation of these databases which are a key factor in the quality of the resulting speech synthesizer. We will focus on the designing of the recording prompts, on the speaker selection procedure, on the recording setup and on the quality control of the resulting database. One of the major challenges was to assure the uniformity of the recordings during the 20 two-hour recording sessions that each speaker had to perform, to produce a total of 13 hours of recorded speech for each of the four speakers. This work was conducted in the scope of the Tecnovoz project that brought together 4 speech research centers and 9 companies with the goal of integrating speech technologies in a wide range of applications.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/741_paper.pdf
Markdown (Informal)
[Methodologies for Designing and Recording Speech Databases for Corpus Based Synthesis](http://www.lrec-conf.org/proceedings/lrec2008/pdf/741_paper.pdf) (Oliveira et al., LREC 2008)
ACL