基于Speech SDK的语音识别技术在三维仿真中的应用  

Application of Speech Recognition Technology in 3D Simulation Based on Speech SDK

作　　者：林鸣霄[1] 

机构地区：[1]同济大学电子与信息技术学院,上海201804

出　　处：《计算机技术与发展》2011年第11期160-162,166,共4页Computer Technology and Development

基　　金：国家863计划重点项目(2010AA122200);上海市科委国际合作项目(10510712500)

摘　　要：随着三维仿真技术的不断发展,简单的人机交互方式已经不能满足人们对仿真环境真实感和沉浸感的要求。针对于此,提出了将基于Speech SDK5.1的语音识别技术应用到三维仿真平台的构想,分析了Speech SDK5.1的工作原理,着重研究了其语音识别接口,对将语音识别应用到三维仿真程序中的可能性和关键技术进行了研究。提出了一种实现动态词汇识别的方法,并通过一个简单的实例展示了实现这类技术的框架和方法,对设计有语音识别功能的三维仿真程序有一定的参考价值。With the continuous development of 3D simulation technology, simply man-machine interactive way cannot satisfy people of simulation environment realism and immersed sense requirements. Based on this,put forward the idea of applying speech recognition tech- nology which based on Speech SDKS. 1 to the 3D simulation platform,analyse the working principle of SDKS. 1 and mainly focus on the speech recognition interface and the ability and key technology of that. Then present a dynamic vocabulary identification method and show the main framework and technology with a simple instance which has certain reference value for designing a 3D simulation program with speech recognition function.

关 键 词：语音识别 三维仿真 SPEECH SDK COM 语音控制 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]