| 面向语音合成的藏语单音素与三音素自动切分算法研究 |
| |
| 引用本文： | 张金溪,李永宏,单广荣,李照耀,江 静.面向语音合成的藏语单音素与三音素自动切分算法研究[J].计算机应用研究,2013,30(11):3272-3275. |
| |
| 作者姓名： | 张金溪 李永宏 单广荣 李照耀 江 静 |
| |
| 作者单位： | 西北民族大学 a. 中国民族语言文字信息技术重点实验室; b. 数学与计算机科学学院, 兰州 730030 |
| |
| 基金项目： | 国家自然科学基金资助项目（61262052）; 西北民族大学中央高校基本科研业务费专项项目（ycx12024） |
| |
| 摘 要： | 在构建藏语语料库时要对语音进行音素切分, 采用了两种方法, 即基于单音素HMM模型的自动切分方法和基于三音素HMM模型的自动切分方法。通过实验分析了这两种HMM模型的自动切分结果的准确率程度, 其中单音素、三音素总的平均切分准确度分别为80. 69%、88. 74%。实验结果表明, 三音素HMM模型的自动切分方法的准确率明显高于单音素HMM模型的切分率, 提高了语音语料库标注信息的精确度和一致性。
|
| 关 键 词： | 语音合成 藏语语料库 单音素 三音素 自动切分 |
Facing speech synthesis for Tibetan single phoneme and triphone automatic cutting algorithms study |
| |
| ZHANG Jin-xi,LI Yong-hong,SHAN Guang-rong,LI Zhao-yao,JIANG Jing.Facing speech synthesis for Tibetan single phoneme and triphone automatic cutting algorithms study[J].Application Research of Computers,2013,30(11):3272-3275. |
| |
| Authors: | ZHANG Jin-xi LI Yong-hong SHAN Guang-rong LI Zhao-yao JIANG Jing |
| |
| Affiliation: | a. Key Laboratory of China's National Linguistic Information Technology, b. Mathematics & Computer Science Institute, Northwest University for Nationalities, Lanzhou 730030, China |
| |
| Abstract: | This paper introduced two methods for phoneme segmentation in Tibetan speech synthesis corpus construction: one was the automatic segmentation method which was based on the mono prime HMM model, the other was the automatic segmentation method which was based on the triphone HMM model. As the analysis to the accuracy of the two HMM automatic segmentation results, it shows that the first method's accuracy is 80. 69% and the second method's is 88. 74%. The experimental results show that segmentation method of the triphone HMM model accuracy is obviously higher than the other. With this method, the accuracy and consistency of the speech corpus has been greatly improved. |
| |
| Keywords: | speech synthesis Tibetan corpus monophonic prime triphone automatic segmentation |
|
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
