Automatic generation of prosodic structure for high quality Mandarin speech synthesis
Resource
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Journal
Fourth International Conference on Spoken Language, 1996. ICSLP 96
Pages
-
Date Issued
1996-10
Date
1996-10
Author(s)
DOI
N/A
Abstract
A key problem for today's speech synthesis technology is to automatically generate an appropriate hierarchical prosodic structure for text input and incorporate it into synthesized speech. The paper presents a method for such a problem in Mandarin Chinese. This method uses a speech database for the training of a statistical model to generate the prosodic structure and determine prosodic parameters such as syllable duration, pause, energy and intonation. The experimental results show that an accuracy of 83.1% in the prediction of prosodic structure can be achieved. Furthermore, a Chinese text-to-speech system can be developed based on the proposed prosodic structure.
SDGs
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00607935.pdf
Size
417.48 KB
Format
Adobe PDF
Checksum
(MD5):829a9db013b8714624a7f909f27d2044