基于语言学知识的发音质量评价算法改进  

The Linguistic Knowledge Based Improvement in Automatic Putonghua Pronunciation Quality Assessment Algorithm

作　　者：刘庆升[1] 魏思[1] 胡郁[1] 郭武[1] 王仁华[1] 

机构地区：[1]中国科学技术大学电子工程与信息科学系讯飞语音实验室,安徽合肥230027

出　　处：《中文信息学报》2007年第4期92-96,共5页Journal of Chinese Information Processing

基　　金：国家语言文学应用"十五"重点科研项目资助(ZDI105-B02)

摘　　要：随着普通话推广工作的深入,采用计算机进行普通话的辅助测试和学习的需求日益迫切。本文针对普通话发音特点,提出了一种改进的基于音素的自动发音质量评价算法。新算法在隐马尔科夫模型的对数后验概率算法基础上,引入普通话发音的语言学知识。与改进前相比,新算法不仅降低了运算量,而且在普通话水平测试的303人现场录音库上,使得机器打分与国家级评测员打分之间的相关度从0.704提升到0.795。With the popularization of Putonghua, the demand for testing and learning by the aid of computer is even more and more intensive. In this paper, we proposed an improved phone-based quality assessment algorithm aiming at Putonghua pronunciation, The linguistic knowledge of Putonghua pronunciation was effectively introduced into the calculation of HMM based log posterior probability. Comparing with traditional method, the proposed one not only reduces the complexity of calculation, but also achieves an improvement of correlation between machine and human scores from 0. 704 to 0, 795 on a database of 303 persons recorded from spot Putonghua Shuiping Ceshi.

关 键 词：计算机应用 中文信息处理 语音识别 发音质量评价 对数后验概率 语言学知识 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]