DocumentCode
1976242
Title
Research on Prosody Modeling in Chinese Speech Synthesis
Author
Jiang Bao-chen ; He Pei-gang
Author_Institution
Sch. of Inf. Eng., Shandong Univ. at Weihai, Weihai, China
fYear
2010
fDate
20-22 Aug. 2010
Firstpage
1
Lastpage
4
Abstract
Prosody model is responsible to predict the quantitive acoustics parameters according to the qualitative prosody information in high level. A predictor was designed and implemented, which can predict the pitch contour, duration and pause of the Chinese syllable. Experiment results show that this model is good enough, and the output speech is more natural than previous system to some extent.
Keywords
speech synthesis; Chinese speech synthesis; Chinese syllable; pitch contour; qualitative prosody information; quantitive acoustics parameters; Acoustics; Artificial neural networks; Conferences; Predictive models; Speech; Speech synthesis;
fLanguage
English
Publisher
ieee
Conference_Titel
Internet Technology and Applications, 2010 International Conference on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-5142-5
Electronic_ISBN
978-1-4244-5143-2
Type
conf
DOI
10.1109/ITAPP.2010.5566215
Filename
5566215
Link To Document