dc.contributor |
Universitat Ramon Llull. La Salle |
dc.contributor.author |
Gonzalvo Fructuoso, Xavier |
dc.contributor.author |
Iriondo Sanz, Ignasi |
dc.contributor.author |
Socoró Carrié, Joan Claudi |
dc.contributor.author |
Alías Pujol, Francesc |
dc.contributor.author |
Monzo Sánchez, Carlos |
dc.date.accessioned |
2021-06-09T20:27:10Z |
dc.date.available |
2021-06-09T20:27:10Z |
dc.date.issued |
2007-05 |
dc.identifier.uri |
http://hdl.handle.net/2072/450141 |
dc.format.extent |
4 p. |
dc.language.iso |
eng |
dc.publisher |
ITRW on Nonlinear Speech Processing, Paris, 22-25 of May 2007 |
dc.rights |
© International Speech Communication Association. Tots els drets reservats |
dc.source |
RECERCAT (Dipòsit de la Recerca de Catalunya) |
dc.subject.other |
Processament de la parla |
dc.subject.other |
Anàlisi prosòdica (Lingüística) |
dc.title |
HMM-based Spanish speech synthesis using CBR as F0 estimator |
dc.type |
info:eu-repo/semantics/conferenceObject |
dc.subject.udc |
62 - Enginyeria. Tecnologia |
dc.embargo.terms |
cap |
dc.rights.accessLevel |
info:eu-repo/semantics/openAccess |
dc.description.abstract |
Hidden 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. |