Pitch models of Mandarin text-to-speech

SHAO Yan-qiu^1,2, SUI Zhi-fang¹, HAN Ji-qing²



Author NameAffiliation

SHAO Yan-qiu Institute of Computational Linguistics, Peking University, Peking 100871, China, ｛yqshao,szf｝@pku.edu.cn
School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001,China 

SUI Zhi-fang Institute of Computational Linguistics, Peking University, Peking 100871, China, ｛yqshao,szf｝@pku.edu.cn 

HAN Ji-qing School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001,China 



Abstract:

The function of prosody model will directly affect the naturalness of synthesized speech. Aimed at the difficulty in generating the pitch contour in prosody model, two pitch models namely corpus-based pitch model and pitch pattern model are deeply studied in this paper. Key problems in the corpus-based model are calculation of the distance and searching of the optimal path with dynamic programming algorithm. For the pitch pattern model, parameters such as pitch pattern, pitch average and pitch range are used to describe the pitch contour, and six pitch patterns are presented. For the generation of pitch contour, the pitch pattern model is more flexible than the corpus-based model. Both of the two models are linked to the real TTS system, and the MOS results of synthesized Mandarin speech show that the pitch pattern model is better than the corpus-based pitch model.

Key words:  speech synthesis  prosody model  pitch model  pitch pattern

DOI：10.11916/j.issn.1005-9113.2009.02.006

Clc Number:TP391.4

Fund: