Acoustic Analysis and Decision Tree-Based Shifting Hierarchical Approach for Prediction of Uyghur Prosodic Boundary  

作　　者：Guljamal Mamateli Askar Hamdulla 

机构地区：[1]School of Mathematical Sciences, Xinjiang Normal University [2]Department of Information Science and Engineering, Xinjiang University

出　　处：《Wuhan University Journal of Natural Sciences》2013年第4期363-368,共6页武汉大学学报（自然科学英文版）

基　　金：Supported by the National Natural Science Foundation of China(61065005and61062008)

摘　　要：Correct prosodic boundary prediction is crucial for the quality of synthesized speech in text-to-speech system. This article mainly presents the prosodic hierarchy of Uyghur language, which belongs to Turkish language family of Altaic language system and further verifies the reliability of proposed Uyghur prosodic boundary annotation rules by acoustic analysis. In the prediction part, a two-layer shifting hierarchical approach based on decision tree is used for predicting prosodic word and prosodic phrase boundary, and the influence of different feature sets on the Uyghur prosodic boundary prediction is also investigated. Experimental results clearly show the acoustical changes and automatic prediction performance of different prosodic boundaries of Uyghur language, thus laying a good foundation for further research.Correct prosodic boundary prediction is crucial for the quality of synthesized speech in text-to-speech system. This article mainly presents the prosodic hierarchy of Uyghur language, which belongs to Turkish language family of Altaic language system and further verifies the reliability of proposed Uyghur prosodic boundary annotation rules by acoustic analysis. In the prediction part, a two-layer shifting hierarchical approach based on decision tree is used for predicting prosodic word and prosodic phrase boundary, and the influence of different feature sets on the Uyghur prosodic boundary prediction is also investigated. Experimental results clearly show the acoustical changes and automatic prediction performance of different prosodic boundaries of Uyghur language, thus laying a good foundation for further research.

关 键 词：Uyghur language acoustic analysis prosodic boundary prediction decision tree 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]