论文讨论了如何选取声学特征来表征不同发音者的语音个人特性。
The paper deals with the selection of acoustic phonetics of the speaker characteristics.
完整的连续语音识别系统主要包括四个部分：特征提取，声学模型，语言模型和搜索算法，本文就是根据这四个部分展开的。
A whole continuous speech recognition system includes four parts: feature extraction, acoustic model, language models and search algorithms, and the thesis is carried out according to them.
笔者运用语音实验的研究方法，考察了大连方言声调新、老两派的单字调和双字调在调长方面的声学特征。
By employing the method of Experimental Phonetics, the author explores the properties of tonal duration of Dalian dialect, based on acoustic data of the old and the new generations.
应用推荐