| 汉语连续变调语音合成算法 |
| |
| 引用本文： | 康广玉,郭世泽,孙圣和.汉语连续变调语音合成算法[J].计算机工程与应用,2009,45(15):28-30. |
| |
| 作者姓名： | 康广玉 郭世泽 孙圣和 |
| |
| 作者单位： | 1.哈尔滨工业大学 自动化测试与控制系，哈尔滨 150001 2.总参54所，北京 100093 |
| |
| 摘 要： | 汉语是声调语言，同一个音节带上不同的声调可以表述不同的语义。发音时两个或两个以上的音节连在一起时，音节所属调类调值所发生变化的现象称为“连读变调”，目前的语音合成系统没有考虑连续变调，使得合成语音自然度不够。采用TD-PSOLA对具有连续变调现象的语音进行合成，实验表明合成语音的自然度较高，是适合小语料库语音合成的良好算法。
|
| 关 键 词： | 连续变调 声调变换 时域基音同步叠加 文语转换 声调模型 |
| 收稿时间： | 2008-12-22 |
| 修稿时间： | 2009-3-2
|
Speech synthesize using Chinese tone sandhi |
| |
| KANG Guang-yu,GUO Shi-ze,SUN Sheng-he.Speech synthesize using Chinese tone sandhi[J].Computer Engineering and Applications,2009,45(15):28-30. |
| |
| Authors: | KANG Guang-yu GUO Shi-ze SUN Sheng-he |
| |
| Affiliation: | 1.Department of Automatic Test and Control，Harbin Institute of Technology，Harbin 150001，China 2.The 54th Research Institute of General Staff，Beijing 100093，China |
| |
| Abstract: | Chinese is a tone language,and the different tone in one same syllable band represents the different meaning.The phenomena that the tone value of tone class in the syllable changes occurs when two or plural syllables of tone language connect each other,and the phenomena is called "tone sandhi".Current speech synthesize systems do not consider the tone sandhi,which causes the naturalness of synthesized speech is not high.This paper synthesizes the speech with the tone sandhi using TD-PSOLA.The experimental r... |
| |
| Keywords: | tone sandhi tone transformation time domain pitch synchronous overlap-add test to speech tone model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
