利用SAPI5完成中文语音音素的分解

Using SAPI 5 to Disassemble Chinese Phoneme

本文讲述了在基于网络的人-人交互系统中,如何利用SAPI5来进行中文语音音素的分解,介绍了SAPI5语音识别(SR)引擎所提供的服务,在一个已经实现的MPEG-4兼容的人脸动画系统基础上,阐述了其在网络人-人交互系统应用中的设计思路和具体相关实现技术。

In this paper, we present a person-to-person interaction system based on computer network, and describe how to disassemble Chinese phoneme using SAPI5 in it. We also discuss the service of speech recognition engine supported in SAPI5.In the MPEG-4 compliant facial animation system, we explain the design and implementation related to person-to-person interaction system based on computer network.