A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis

In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality pros...

ver descrição completa

Detalhes bibliográficos
Autores: Iriondo, Ignasi, Alías-Pujol, Francesc, Sanchís Bernabeu, Francisco Javier, Melenchón, Javier
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2003
País:España
Recursos:Universitat Ramon Llull (URL)
Repositorio:DAU Arxiu Digital de la Universitat Ramon Llull
OAI Identifier:oai:dau.url.edu:20.500.14342/2892
Acesso em linha:http://hdl.handle.net/20.500.14342/2892
Access Level:acceso abierto
Palavra-chave:Parla
Processament de la parla
id ES_2d46497d563b01264fe0c8f86a93eb47
oai_identifier_str oai:dau.url.edu:20.500.14342/2892
network_acronym_str ES
network_name_str España
repository_id_str
spelling A Hybrid Method Oriented to Concatenative Text-to-Speech SynthesisIriondo, IgnasiAlías-Pujol, FrancescSanchís Bernabeu, Francisco JavierMelenchón, JavierParlaProcessament de la parlaIn this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.8th European Conference on Speech Communication and Technology. EUROSPEECH 2003 - INTERSPEECH 2003Universitat Ramon Llull. La Salle20202023202020232003info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersion4 p.application/pdfhttp://hdl.handle.net/20.500.14342/2892RECERCAT (Dipòsit de la Recerca de Catalunya)reponame:DAU Arxiu Digital de la Universitat Ramon Llullinstname:Universitat Ramon Llull (URL)Inglésinfo:eu-repo/grantAgreement/DURSI/FI/2000 FI-00679© ISCA. Tots els drets reservatsinfo:eu-repo/semantics/openAccessoai:dau.url.edu:20.500.14342/28922026-06-21T06:40:37Z
dc.title.none.fl_str_mv A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
title A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
spellingShingle A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
Iriondo, Ignasi
Parla
Processament de la parla
title_short A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
title_full A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
title_fullStr A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
title_full_unstemmed A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
title_sort A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
dc.creator.none.fl_str_mv Iriondo, Ignasi
Alías-Pujol, Francesc
Sanchís Bernabeu, Francisco Javier
Melenchón, Javier
author Iriondo, Ignasi
author_facet Iriondo, Ignasi
Alías-Pujol, Francesc
Sanchís Bernabeu, Francisco Javier
Melenchón, Javier
author_role author
author2 Alías-Pujol, Francesc
Sanchís Bernabeu, Francisco Javier
Melenchón, Javier
author2_role author
author
author
dc.contributor.none.fl_str_mv Universitat Ramon Llull. La Salle
dc.subject.none.fl_str_mv Parla
Processament de la parla
topic Parla
Processament de la parla
description In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.
publishDate 2003
dc.date.none.fl_str_mv 2003
2020
2020
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.14342/2892
url http://hdl.handle.net/20.500.14342/2892
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/DURSI/FI/2000 FI-00679
dc.rights.none.fl_str_mv © ISCA. Tots els drets reservats
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © ISCA. Tots els drets reservats
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 4 p.
application/pdf
dc.publisher.none.fl_str_mv 8th European Conference on Speech Communication and Technology. EUROSPEECH 2003 - INTERSPEECH 2003
publisher.none.fl_str_mv 8th European Conference on Speech Communication and Technology. EUROSPEECH 2003 - INTERSPEECH 2003
dc.source.none.fl_str_mv RECERCAT (Dipòsit de la Recerca de Catalunya)
reponame:DAU Arxiu Digital de la Universitat Ramon Llull
instname:Universitat Ramon Llull (URL)
instname_str Universitat Ramon Llull (URL)
reponame_str DAU Arxiu Digital de la Universitat Ramon Llull
collection DAU Arxiu Digital de la Universitat Ramon Llull
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405304154750976
score 15,300719

Registos relacionados