Analysis and synthesis of the four tones in connected speech of the standard Chinese based on a command-response model
Analysis and synthesis of the four tones in connected speech of the standard Chinese based on a command-response model
复制标题
基于命令-反应模型的普通话连语四声分析与综合
DOI：
10.21437/eurospeech.1999-376
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
Tomohiro Kodama
中科院分区：
文献类型：
--
作者：
Changfu Wang;H. Fujisaki;S. Ohno;Tomohiro Kodama
汉语是典型的声调语言，一个音节具有多个声调类型，可以代表不同的语素。这些声调类型在单个音节的基频曲线上有较为明显的表现，而在连续语音中，由于受相邻音节声调、整个话语的句法和语用信息等因素的影响，声调类型的变化很大。本文用命令-反应模型分析了普通话声调的F_0曲线，结果表明声调命令的时间与音节的“元音+尾音”部分之间存在着系统的关系。结果，然后用于推导规则的音调命令生成语音合成。合成语音韵律的自然性证实了规则的有效性。
The Chinese language is a typical tone language in which a syllablepossesses severaltone typesand thus canrepresent different morphemes. While these tone types have rather clear manifestations in the fundamental frequency contour in isolated syllables, they vary considerably in connected speech due to the influences of such factors as tones of adjacent syllables, syntactic and pragmatic information of the whole utterance. This paper describes the results of analysis of F 0 contours of the Standard Chinese using a command-response model, and shows that systematic relationships exit between the timing of the tone commands and the “vowel plus coda” part of a syllable. The results are then used to derive rules for tone command generation in speech synthesis. The validity of the rules has been confirmed by the naturalness of prosody of synthetic speech.