Show simple item record

dc.contributorUniversitat Ramon Llull. La Salle
dc.contributor.authorGonzalvo Fructuoso, Xavier
dc.contributor.authorIriondo Sanz, Ignasi
dc.contributor.authorSocoró Carrié, Joan Claudi
dc.contributor.authorAlías Pujol, Francesc
dc.contributor.authorMonzo Sánchez, Carlos
dc.date.accessioned2021-06-09T20:27:10Z
dc.date.accessioned2023-07-13T09:53:12Z
dc.date.available2021-06-09T20:27:10Z
dc.date.available2023-07-13T09:53:12Z
dc.date.issued2007-05
dc.identifier.urihttp://hdl.handle.net/20.500.14342/2977
dc.description.abstractHidden Markov Models based text-to-speech (HMM-TTS) syn thesis is a technique for generating speech from trained statisti cal models where spectrum, pitch and durations of basic speech units are modelled altogether. The aim of this work is to de scribe a Spanish HMM-TTS system using CBR as a F0 esti mator, analysing its performance objectively and subjectively. The experiments have been conducted on a reliable labelled speech corpus, whose units have been clustered using contex tual factors according to the Spanish language. The results show that the CBR-based F0 estimation is capable of improving the HMM-based baseline performance when synthesizing non declarative short sentences and reduced contextual information is available.eng
dc.format.extent4 p.cat
dc.language.isoengcat
dc.publisherITRW on Nonlinear Speech Processing, Paris, 22-25 of May 2007cat
dc.rights© International Speech Communication Association. Tots els drets reservats
dc.sourceRECERCAT (Dipòsit de la Recerca de Catalunya)
dc.subject.otherProcessament de la parlacat
dc.subject.otherAnàlisi prosòdica (Lingüística)cat
dc.titleHMM-based Spanish speech synthesis using CBR as F0 estimatorcat
dc.typeinfo:eu-repo/semantics/conferenceObjectcat
dc.rights.accessLevelinfo:eu-repo/semantics/openAccess
dc.embargo.termscapcat
dc.subject.udc62


Files in this item

 

This item appears in the following Collection(s)

Show simple item record

Share on TwitterShare on LinkedinShare on FacebookShare on TelegramShare on WhatsappPrint