In the thesis, the Mandarin broadcast news corpus, MATBN, was adopted to train the acoustic model at first.And the models for spontaneous phenomena were built by making use of this corpus, too.

• 在本论文中，我们首先利用广播新闻语料库（MATBN）依据语者环境个别建立声学模型，并利用其中自发性语音现象，训练出相对应的声学模型，作为基本辨识系统。