@inproceedings{garcia-etal-2006-joint,
title = "A joint prosody evaluation of {F}rench text-to-speech synthesis systems",
author = {Garcia, Marie-Neige and
d{'}Alessandro, Christophe and
Bailly, G{\'e}rard and
Boula de Mare{\"u}il, Philippe and
Morel, Michel},
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/817_pdf.pdf",
abstract = "This paper reports on prosodic evaluation in the framework of the EVALDA/EvaSy project for text-to-speech (TTS) evaluation for the French language. Prosody is evaluated using a prosodic transplantation paradigm. Intonation contours generated by the synthesis systems are transplanted on a common segmental content. Both diphone based synthesis and natural speech are used. Five TTS systems are tested along with natural voice. The test is a paired preference test (with 19 subjects), using 7 sentences. The results indicate that natural speech obtains consistently the first rank (with an average preference rate of 80{\%}), followed by a selection based system (72{\%}) and a diphone based system (58{\%}). However, rather large variations in judgements are observed among subjects and sentences, and in some cases synthetic speech is preferred to natural speech. These results show the remarkable improvement achieved by the best selection based synthesis systems in terms of prosody. In this way; a new paradigm for evaluation of the prosodic component of TTS systems has been successfully demonstrated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-etal-2006-joint">
<titleInfo>
<title>A joint prosody evaluation of French text-to-speech synthesis systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Neige</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">d’Alessandro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gérard</namePart>
<namePart type="family">Bailly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Boula de Mareüil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Morel</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 reports on prosodic evaluation in the framework of the EVALDA/EvaSy project for text-to-speech (TTS) evaluation for the French language. Prosody is evaluated using a prosodic transplantation paradigm. Intonation contours generated by the synthesis systems are transplanted on a common segmental content. Both diphone based synthesis and natural speech are used. Five TTS systems are tested along with natural voice. The test is a paired preference test (with 19 subjects), using 7 sentences. The results indicate that natural speech obtains consistently the first rank (with an average preference rate of 80%), followed by a selection based system (72%) and a diphone based system (58%). However, rather large variations in judgements are observed among subjects and sentences, and in some cases synthetic speech is preferred to natural speech. These results show the remarkable improvement achieved by the best selection based synthesis systems in terms of prosody. In this way; a new paradigm for evaluation of the prosodic component of TTS systems has been successfully demonstrated.</abstract>
<identifier type="citekey">garcia-etal-2006-joint</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/817_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A joint prosody evaluation of French text-to-speech synthesis systems
%A Garcia, Marie-Neige
%A d’Alessandro, Christophe
%A Bailly, Gérard
%A Boula de Mareüil, Philippe
%A Morel, Michel
%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 garcia-etal-2006-joint
%X This paper reports on prosodic evaluation in the framework of the EVALDA/EvaSy project for text-to-speech (TTS) evaluation for the French language. Prosody is evaluated using a prosodic transplantation paradigm. Intonation contours generated by the synthesis systems are transplanted on a common segmental content. Both diphone based synthesis and natural speech are used. Five TTS systems are tested along with natural voice. The test is a paired preference test (with 19 subjects), using 7 sentences. The results indicate that natural speech obtains consistently the first rank (with an average preference rate of 80%), followed by a selection based system (72%) and a diphone based system (58%). However, rather large variations in judgements are observed among subjects and sentences, and in some cases synthetic speech is preferred to natural speech. These results show the remarkable improvement achieved by the best selection based synthesis systems in terms of prosody. In this way; a new paradigm for evaluation of the prosodic component of TTS systems has been successfully demonstrated.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/817_pdf.pdf
Markdown (Informal)
[A joint prosody evaluation of French text-to-speech synthesis systems](http://www.lrec-conf.org/proceedings/lrec2006/pdf/817_pdf.pdf) (Garcia et al., LREC 2006)
ACL