摘要： 主要研究了语音使能的多模态输入Web应用的系统架构和运行机制?该系统在传 统Web交互模式的基础上引入了分布式语音识别功能模块,使手持移动设备的用户可以同时 使用语音和其他传统输入方式获得无线因特网的信息服务?

关键词: 多模态人机界面, 分布式语音识别, 语音特征, Web, XML

Abstract: A speech enabled system architecture and mechanism for multi-modal i nput Web interaction is proposed. This system extends the traditional Web intera ction modal and imports the distributed speech recognition (DSR) module to make mobile users enjoy wireless Internet services by speech and other traditional in put methods.

中图分类号: 

• TN912.3