Prosody modelling of spanish for expressive speech synthesis

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

8 Citas (Scopus)

Resumen

This paper presents the use of analogical learning, in particular case-based reasoning, for the automatic generation of prosody from text, which is automatically tagged with prosodic features. This is a corpus-based method for quantitative modelling of prosody to be used in a Spanish text to speech system. The main objective is the development of a method for predicting the three main prosodic parameters: the fundamental frequency (F0) contour, the segmental duration and energy. Both objective and subjective experiments have been conducted in order to evaluate the accuracy of our proposal.

Idioma originalInglés
Título de la publicación alojada2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas821-824
Número de páginas4
ISBN (versión impresa)1424407281, 9781424407286
DOI
EstadoPublicada - 2007
Evento2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, Estados Unidos
Duración: 15 abr 200720 abr 2007

Serie de la publicación

NombreICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volumen4
ISSN (versión impresa)1520-6149

Conferencia

Conferencia2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
País/TerritorioEstados Unidos
CiudadHonolulu, HI
Período15/04/0720/04/07

Huella

Profundice en los temas de investigación de 'Prosody modelling of spanish for expressive speech synthesis'. En conjunto forman una huella única.

Citar esto