本文以带有韵律标注的语料库ASCCD为基础,从语音信号分析的角度,研究了汉语普通话韵律间断模式在语音的时长、基频和音强等三个方面的表现特征,并在大量统计分析的基础上建立了识别分类的决策树模型,实验证明,这些特征能较好地描述朗读话语的韵律间断模式。
Abstract
Based on large speech corpus (ASCCD) with prosodic structure label ,this paper presents some statistic result on acoustic parameter of prosodic boundary. We study the syllable duration ,intensity and pitch at the boundary and select a serial of acoustic parameter to train a CART. The result shows that the parameter characterize acoustic feature of the prosodic boundary and the trained CART can classify different boundary efficiency. So it is possible to train statistical model for prosodic boundary location in Mandarin ,this is very important both for speech recognition and synthesis.
关键词
韵律边界 /
韵律结构 /
决策树
{{custom_keyword}} /
Key words
Prosodic Boundary /
Prosodic Structure /
CART(Classification And Regression Trees)
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李爱军. 普通话口语对话的韵律特性声学分析,第四届全国现代语音学会论文集,1999
[2] 林茂灿. 普通话语句中间断和语句韵律短语,当代语言学,2000 ,2 (4) :210 - 217
[3] 杨玉芳.句法边界的韵律征兆,声学学报,1997 ,22 (4)
[4] Ki-Wan Eom ,Jin-Young Kim , and Sun Mi Kim ,A primary study on the randomness control of the prosodic boundary index for natural synthetic speech. Eurospeech’97
[5] Li Aijun ,A national database design for speech synthesis and prosodic labeling of standard Chinese , In proceedings of oriental COCDA’99 ,TaiPei ,TaiWan ,1999
[6] Lin Maocan ,The acoustic manifestation of prosodic phrase boundaries in Standard Chinese , Proc. of Conference on Phonetics of the Languages in China ,City University of Hong Kong ,1998
[7] M. Ostendorf ,N. Veilleux ,A hierarchical Stochastic Model for Automatic Prediction of prosodic Boundary Location. Computational Linguistics ,1994 ,20 (1) :21 - 54
[8] Wang Pei ,Yang Yufang Prosodic Structure and Syntactic Structure ,The proceedings of the third international Conference on Cognitive Science ,2001 ,491 - 496
[9] Xipeng Shen ,Bo Xu. A CART-Based Hierarchical Stochastic Model for Prosodic Phrasing in Chinese , ISCSLP’00 ,Beijing ,2000 ,105 - 109
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家973项目(G1998030504);国家自然基金重点项目(69835003)
{{custom_fund}}
PDF(241 KB)
