@inproceedings{lazaridis-etal-2010-vergina,
title = "{V}ergina: A {M}odern {G}reek Speech Database for Speech Synthesis",
author = "Lazaridis, Alexandros and
Kostoulas, Theodoros and
Ganchev, Todor and
Mporas, Iosif and
Fakotakis, Nikos",
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/614_Paper.pdf",
abstract = "The present paper outlines the Vergina speech database, which was developed in support of research and development of corpus-based unit selection and statistical parametric speech synthesis systems for Modern Greek language. In the following, we describe the design, development and implementation of the recording campaign, as well as the annotation of the database. Specifically, a text corpus of approximately 5 million words, collected from newspaper articles, periodicals, and paragraphs of literature, was processed in order to select the utterances-sentences needed for producing the speech database and to achieve a reasonable phonetic coverage. The broad coverage and contents of the selected utterances-sentences of the database ― text corpus collected from different domains and writing styles ― makes this database appropriate for various application domains. The database, recorded in audio studio, consists of approximately 3,000 phonetically balanced Modern Greek utterances corresponding to approximately four hours of speech. Annotation of the Vergina speech database was performed using task-specific tools, which are based on a hidden Markov model (HMM) segmentation method, and then manual inspection and corrections were performed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lazaridis-etal-2010-vergina">
<titleInfo>
<title>Vergina: A Modern Greek Speech Database for Speech Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Lazaridis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodoros</namePart>
<namePart type="family">Kostoulas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Todor</namePart>
<namePart type="family">Ganchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iosif</namePart>
<namePart type="family">Mporas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Fakotakis</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>The present paper outlines the Vergina speech database, which was developed in support of research and development of corpus-based unit selection and statistical parametric speech synthesis systems for Modern Greek language. In the following, we describe the design, development and implementation of the recording campaign, as well as the annotation of the database. Specifically, a text corpus of approximately 5 million words, collected from newspaper articles, periodicals, and paragraphs of literature, was processed in order to select the utterances-sentences needed for producing the speech database and to achieve a reasonable phonetic coverage. The broad coverage and contents of the selected utterances-sentences of the database ― text corpus collected from different domains and writing styles ― makes this database appropriate for various application domains. The database, recorded in audio studio, consists of approximately 3,000 phonetically balanced Modern Greek utterances corresponding to approximately four hours of speech. Annotation of the Vergina speech database was performed using task-specific tools, which are based on a hidden Markov model (HMM) segmentation method, and then manual inspection and corrections were performed.</abstract>
<identifier type="citekey">lazaridis-etal-2010-vergina</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/614_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vergina: A Modern Greek Speech Database for Speech Synthesis
%A Lazaridis, Alexandros
%A Kostoulas, Theodoros
%A Ganchev, Todor
%A Mporas, Iosif
%A Fakotakis, Nikos
%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 lazaridis-etal-2010-vergina
%X The present paper outlines the Vergina speech database, which was developed in support of research and development of corpus-based unit selection and statistical parametric speech synthesis systems for Modern Greek language. In the following, we describe the design, development and implementation of the recording campaign, as well as the annotation of the database. Specifically, a text corpus of approximately 5 million words, collected from newspaper articles, periodicals, and paragraphs of literature, was processed in order to select the utterances-sentences needed for producing the speech database and to achieve a reasonable phonetic coverage. The broad coverage and contents of the selected utterances-sentences of the database ― text corpus collected from different domains and writing styles ― makes this database appropriate for various application domains. The database, recorded in audio studio, consists of approximately 3,000 phonetically balanced Modern Greek utterances corresponding to approximately four hours of speech. Annotation of the Vergina speech database was performed using task-specific tools, which are based on a hidden Markov model (HMM) segmentation method, and then manual inspection and corrections were performed.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/614_Paper.pdf
Markdown (Informal)
[Vergina: A Modern Greek Speech Database for Speech Synthesis](http://www.lrec-conf.org/proceedings/lrec2010/pdf/614_Paper.pdf) (Lazaridis et al., LREC 2010)
ACL
- Alexandros Lazaridis, Theodoros Kostoulas, Todor Ganchev, Iosif Mporas, and Nikos Fakotakis. 2010. Vergina: A Modern Greek Speech Database for Speech Synthesis. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).