Mostra el registre parcial de l'element

dc.contributorUniversitat Ramon Llull. La Salle
dc.contributor.authorAlías Pujol, Francesc
dc.contributor.authorSocoró Carrié, Joan Claudi
dc.contributor.authorSevillano Domínguez, Xavier
dc.contributor.authorIriondo Sanz, Ignasi
dc.contributor.authorGonzalvo Fructuoso, Xavier
dc.date.accessioned2020-07-02T08:50:09Z
dc.date.accessioned2023-07-13T09:51:47Z
dc.date.available2020-07-02T08:50:09Z
dc.date.available2023-07-13T09:51:47Z
dc.date.issued2006-09-17
dc.identifier.urihttp://hdl.handle.net/20.500.14342/2869
dc.description.abstractThis paper describes a multi-domain text-to-speech (MD-TTS)synthesis strategy for generating speech among different domainsand so increasing the flexibility of high quality TTS systems. Tothat effect, the MD-TTS introduces a flexible TTS architecture thatincludes an automatic domain classification module, which allowsMD-TTS systems to be implemented by different synthesis strate-gies and speech corpus typologies. In this work, the performanceof a corpus-based MD-TTS system is subjectively validated bymeans of several perceptual testseng
dc.format.extent4 p.cat
dc.language.isoengcat
dc.publisherNinth International Conference on Spoken Language Processing. INTERSPEECH 2006cat
dc.rights© L'autor/a. Tots els drets reservats
dc.sourceRECERCAT (Dipòsit de la Recerca de Catalunya)
dc.subject.otherParlacat
dc.subject.otherProcessament de la parlacat
dc.titleMulti-domain Text-to-Speech Synthesis by Automatic Text Classificationcat
dc.typeinfo:eu-repo/semantics/articlecat
dc.typeinfo:eu-repo/semantics/publishedVersioncat
dc.rights.accessLevelinfo:eu-repo/semantics/openAccess
dc.embargo.termscapcat
dc.relation.projectIDinfo:eu-repo/grantAgreement/MITYC/FIT-350301-2004-2cat


Fitxers en aquest element

 

Aquest element apareix en la col·lecció o col·leccions següent(s)

Mostra el registre parcial de l'element

Comparteix a TwitterComparteix a LinkedinComparteix a FacebookComparteix a TelegramComparteix a WhatsappImprimeix