Abstract: The impression of naturalness that issues from a TTS system is a function of the richness of the melodic contours and the quality of the rhythmic patterns it is able to apply to the speech it produces. The prosody generator is responsible for these two aspects. We shall now examine its requirements and examine how its goals can be partially achieved, after some definitions and a few words on the difficulty of deriving a consistent model of prosody.
Publication Year: 1997
Publication Date: 1997-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 1
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot