中文摘要：

本文通过电磁发音仪（Electro Magnetic Articulography,EMA）AG500,以200帧/秒的采样率采集了英语和汉语的标准发音动作数据,然而,交叉语言比较的首要任务就是要消除特定说话人声道特性及其它个人生理特性等音素而引起的固有差别,本文采用了基于说话人归一化的普氏算法来进行说话人归一化处理,获得了英汉相似音素发音的元音对比最小对,最后成功揭示了2种语言易混淆元音发音文本对在口腔内外发音动作上的区别。

英文摘要：

In this paper,English and Mandarin＇s standard articulatory movement are collected by the Electro-Magnetic-Articulography（ EMA） AG500 every 5 msec. However,the first task of cross linguistic comparison is to eliminate the variability which came from speaker-specific vocal-tract structure and the other individual biomechanical properties. This paper uses the speaker normalization based procrustes to realize speaker normalization,so as to obtain bilingual vowel and consonant mini-pairs respectively. After that,bilingual confusing pronunciation vowel text pairs＇ differences of internal and external motions are revealed successfully.