Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10609/92577
Título : | Voice quality modelling for expressive speech synthesis |
Autoría: | Monzo, Carlos Iriondo, Ignasi Socoró, Joan Claudi |
Otros: | Universitat Ramon Llull Universitat Oberta de Catalunya (UOC) |
Citación : | Monzo, C., Iriondo, I. & Socoró, J. C. (2014). Voice quality modelling for expressive speech synthesis. The Scientific World Journal, 2014(). doi: 10.1155/2014/627189 |
Resumen : | This paper presents the perceptual experiments that were carried out in order to validate the methodology of transforming expressive speech styles using voice quality (VoQ) parameters modelling, along with the well-known prosody (F0, duration, and energy), from a neutral style into a number of expressive ones. The main goal was to validate the usefulness of VoQ in the enhancement of expressive synthetic speech in terms of speech quality and style identification. A harmonic plus noise model (HNM) was used to modify VoQ and prosodic parameters that were extracted from an expressive speech corpus. Perception test results indicated the improvement of obtained expressive speech styles using VoQ modelling along with prosodic characteristics. |
Palabras clave : | calidad de voz habla sintética |
DOI: | 10.1155/2014/627189 |
Tipo de documento: | info:eu-repo/semantics/article |
Versión del documento: | info:eu-repo/semantics/publishedVersion |
Fecha de publicación : | 22-ene-2014 |
Licencia de publicación: | http://creativecommons.org/licenses/by/3.0/es/ |
Aparece en las colecciones: | Articles cientÍfics Articles |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
voice.pdf | 1,46 MB | Adobe PDF | Visualizar/Abrir |
Comparte:
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons