本文论述了采用统计模型进行汉语韵律层级结构分析和韵律建模的思路,在此基础上建立了汉语语音合成系统。其中,本文还仔细阐述了韵律代价函数的构造,及其参数的自动训练算法。同时,论文还分析了韵律特征间相互作用对音节基元选取的影响,并最终实现了一个连续语流中用于汉语语音合成的音节基元选取模型。测试表明了本文提出的基于统计模型的韵律层级分析和韵律建模思路,能够较好应用于汉语语音合成系统的构造,并使之具有良好的合成语音的自然度。
Abstract
The paper describes the methods of Chinese Prosodic Hierarchy Analysis and Prosody Modeling ,which are based on statistic algorithm. Meanwhile ,the paper also describes the prosody cost function and corresponding training method for the parameters. Furthermore ,the interaction among the prosodic features is analyzed in respond to its influence in speech unit selection procedure.Based on these ,a Chinese Syllable Unit Selection Model was generated for the spontaneous speech synthesis system. The tests show that the method described in the paper is much suitable to the constitution of Speech Synthesis System and improves the naturalness of the synthesis result a lot .
关键词
汉语韵律层级结构 /
韵律建模 /
韵律代价函数
{{custom_keyword}} /
Key words
Chinese Prosodic Hierarchy /
Prosody Modeling /
Prosody Cost Function
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Selkirk ,E. Phonology and syntax :the relation between sound and structure. MIT press ,1984
[2] Achim Mueller ,Jianhua Tao ,Ruediger Hoffmann ,Data-driven importance analysis of linguistic and phonetic information , ICSLP2000
[3] 吴宗济. 普通话三字组变调规律. 中国语言学报,1985 ,第二期
[4] 沈炯. 从轻音现象看语音与语法研究的关系. 吕淑湘等.《语法研究入门》. 商务印书馆,1999 ,158页
[5] 林茂灿,颜景助. 普通话轻声与轻重音. 语言教学与研究,1990年第3期
[6] 陶建华,蔡莲红等. 汉语TTS系统中可训练韵律模型的研究. 声学学报,第26卷:67 - 72
[7] 林茂灿,颜景助. 北京话轻声的声学性质. 方言. 1980年第3期
[8] Andrew J . Hunt and Alan W. Black ,"Unit selection in a concatenative speech synthesis system using a large speech database", ICASSP 96
[9] 孙茂松等. 消解中文三字长交集型分词歧义的算法. 清华大学学报,1999 ,39 (5)
[10] 王政红. 论双音复合词的构成格式. 南京理工大学学报,1997 ,10 (6)
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(69875008)
{{custom_fund}}
PDF(418 KB)
