英语作为第二语言的多媒体语音数据库设计制作及初步测试

A Design Execution and First Testing of Multimedia English Database of Second Language

由于中国方言的发音不同,从而影响了作为第二语言的英语发音也出现了不同的特色,与第一语言为英语的发音口型也出现了很大的差别,在英语的普及的今天,以英文作为第二语言的人们也日益增多,因而有必要建立一个专门针对英语为第二语言的多媒体语音数据库.本数据库参照AVICAR[1]的方法进行收集,介绍了数据库的特点、录音内容、存储形式,最后对该数据库进行初步辨认测试,并将测试结果与标准测试的结果进行比较.初步测试结果发现收集的数据库识别率大大降低,可见建立该数据库是很有必要的.

The pronunciation of dialect in China is very different, so the pronunciation and the degree of lip rounding of English as a second language showed different features, and with the popularization of English, people who use English as a second language are increasing greatly. So it is necessary to establish a speech database for English as a second language. This database adopts the method of AVICAR. In this paper, it introduces the characteristics of recording, the form of data, the proceeding and the testing of this collected database. Finally the collected database is compared with the standard result testing. The recognition of rate fell greatly in the experimental result, so this database needs to be built.