面向语音合成的藏语单音素与三音素自动切分算法研究  

Facing speech synthesis for Tibetan single phoneme and triphone automatic cutting algorithms study

作　　者：张金溪[1] 李永宏[1] 单广荣[2] 李照耀[1] 江静[1] 

机构地区：[1]西北民族大学中国民族语言文字信息技术重点实验室,兰州730030 [2]西北民族大学数学与计算机科学学院,兰州730030

出　　处：《计算机应用研究》2013年第11期3272-3275,共4页Application Research of Computers

基　　金：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。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.

关 键 词：语音合成 藏语语料库 单音素 三音素 自动切分 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]