In this paper, the prosodic control strategy is discussed under the collectivity of Chinese TTS system design. A four level (syllable, prosodic word, prosodic phrase and sentence) pitch modification and multiplicative duration model are suggested. Although the prototype of models was formed in 1994, the subsequent results of concerned research based on large speech databases are also represented, which effectively advance to perfect the prosody control mode of the Chinese TTS system.
Cite as: Lu, S., He, L., Yang, Y., Cao, J. (2000) Prosodic control in Chinese TTS system. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 21-24, doi: 10.21437/ICSLP.2000-6
@inproceedings{lu00_icslp,
author={Shinan Lu and Lin He and Yufang Yang and Jianfen Cao},
title={{Prosodic control in Chinese TTS system}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 1, 21-24},
doi={10.21437/ICSLP.2000-6}
}