Title :
Prosody Modelling of Spanish for Expressive Speech Synthesis
Author :
Iriondo, Ignasi ; Socoro, Joan Claudi ; Alias, Francesc
Author_Institution :
Dept. of Commun. & Signal Theory, Ramon Llull Univ., Barcelona
Abstract :
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.
Keywords :
speech synthesis; Spanish text; analogical learning; automatic prosody generation; case-based reasoning; corpus-based method; expressive speech synthesis; fundamental frequency contour; prosodic features; prosody modelling; quantitative modelling; Context modeling; Frequency; Humans; Natural languages; Proposals; Root mean square; Semiconductor device modeling; Signal generators; Speech processing; Speech synthesis; Speech synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0727-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2007.367039
