摘要
本文研究了由计算机输入汉语拼音字符,以汉语音素作为声元素,根据语音的韵律规则合成连续汉语语声的方法。该方法数据量少,便于控制语音、语调。实验表明,利用该方法构成汉语文-语转换系统是可行的。
In this paper a Chinese Text-to-Speech Synthesis-by-rule system has been described. The standard Pin-Yin system is used for input by a conventional keyboard. The Chinese phonemes are used as the phonetic units. We control parameters of the formant synthesizer by using speech data and phonetic rules to produce continuous speech. This Text-to-Speech conversion system is characterised by small data storage as well as flexibility in controlling phonetic value and tones. The experiments present that it is possible to form a Chinese Text-to-Speech system using the scheme described in this paper.
出处
《声学学报》
EI
CSCD
北大核心
1990年第3期194-201,共8页
Acta Acustica
