Modeling and synthesizing emotional speech for catalan text-to-speech synthesis

Ignasi Iriondo, Francesc Alias, Javier Melenchon, M. Angeles Llorca

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

9 Citas (Scopus)

Resumen

This paper describes an initial approach to emotional speech synthesis in Catalan based on a diphone concatenation TTS system. The main goal of this work is to develop a simple prosodic model for expressive synthesis. This model is obtained from an emotional speech collection artificially generated by means of a copy-prosody experiment. After validating the emotional content of this collection, the model was automated and incorporated into our TTS system. Finally, the automatic speech synthesis system has been evaluated by means of a perceptual test, obtaining encouraging results.

Idioma originalInglés
Título de la publicación alojadaAffective Dialogue Systems
EditoresElisabeth Andre, Laila Dybkjær, Wolfgang Minker, Paul Heisterkamp
EditorialSpringer Verlag
Páginas197-208
Número de páginas12
ISBN (versión impresa)3540221433, 9783540221432
DOI
EstadoPublicada - 2004
Publicado de forma externa
EventoTutorial and Research Workshop on Affective Dialogue Systems, ADS 2004 - Kloster Irsee, Alemania
Duración: 14 jun 200416 jun 2004

Serie de la publicación

NombreLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volumen3068
ISSN (versión impresa)0302-9743

Conferencia

ConferenciaTutorial and Research Workshop on Affective Dialogue Systems, ADS 2004
País/TerritorioAlemania
CiudadKloster Irsee
Período14/06/0416/06/04

Huella

Profundice en los temas de investigación de 'Modeling and synthesizing emotional speech for catalan text-to-speech synthesis'. En conjunto forman una huella única.

Citar esto