Mostrar el registro sencillo del ítem

dc.contributorUniversitat Ramon Llull. La Salle
dc.contributorIllinois Genetic Algorithms Lab
dc.contributorUniversity of Illinois. National Center for Supercomputing Applications
dc.contributor.authorAlías Pujol, Francesc
dc.contributor.authorLlorà Fàbrega, Xavier
dc.date.accessioned2020-07-06T12:36:58Z
dc.date.accessioned2023-07-13T09:52:06Z
dc.date.available2020-07-06T12:36:58Z
dc.date.available2023-07-13T09:52:06Z
dc.date.issued2003-09-01
dc.identifier.urihttp://hdl.handle.net/20.500.14342/2896
dc.description.abstractUnit selection text-to-speech (TTS) conversion is an ongoingresearch for the speech synthesis community. This paper isfocused on tuning the weights involved in the target and con-catenation cost metrics. We propose a method for automati-cally adjusting these weights simultaneously by means of di-phone and triphone pairs. This method is based on techniquesprovided by the evolutionary computation community, takingadvantage of their robustness in noisy domains. The experi-ments and their analyses demonstrate its good performance inthis problem, thus, overcoming some constraints assumed byprevious works and leading to a new interesting framework forfurther investigations.eng
dc.format.extent4 p.
dc.language.isoeng
dc.publisher8th European Conference on Speech Communication and Technology. EUROSPEECH 2003 - INTERSPEECH 2003
dc.rights© ISCA. Tots els drets reservats
dc.sourceRECERCAT (Dipòsit de la Recerca de Catalunya)
dc.subject.otherProcessament de la parla
dc.subject.otherParla
dc.titleEvolutionary weight tuning based on diphone pairsfor unit selection speech synthesis
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.rights.accessLevelinfo:eu-repo/semantics/openAccess
dc.embargo.termscap
dc.relation.projectIDinfo:eu-repo/grantAgreement/DURSI/FI/2000 FI-00679


Ficheros en el ítem

 

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Compartir en TwitterCompartir en LinkedinCompartir en FacebookCompartir en TelegramCompartir en WhatsappImprimir