In this paper, a novel approach based on time-domain pitch-synchronous point-to-point (TD-PSPTP) model for speech synthesis is presented. Compared to TD-PSOLA, which is currently one of the most popular concatenation methods, TD-PSPTP model provides a wider range of pitch and time modification. The quality of synthesized speech by TD-PSPTP shows to be high, especially its capability of overcoming reverberation, existing in TD-PSOLA when there is a drastic prosodic modification. The computational expense of TD-PSPTP model is no higher than that of TD-PSOLA. It provides an efficient way for the real time implementation of synthesis system.
Cite as: Huang, Y., Xu, B. (1999) A novel model TD-PSPTP for speech synthesis. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2303-2306, doi: 10.21437/Eurospeech.1999-502
@inproceedings{huang99e_eurospeech,
author={Yan Huang and Bo Xu},
title={{A novel model TD-PSPTP for speech synthesis}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2303--2306},
doi={10.21437/Eurospeech.1999-502}
}