基于语音识别的计算机声图系统  

A Computer Speech-graphics System Based on Speech Recognition

作　　者：薛啸宇[1] 柳玉昌 赵金龙 

机构地区：[1]国防科技大学电子技术系

出　　处：《国防科技大学学报》1992年第3期70-73,79,共5页Journal of National University of Defense Technology

摘　　要：本文提出一种计算机声图系统的模型,阐述了它的原理,并以TI-SPEECH语音处理系统、KX-600图形显示系统和IBM PC/AT计算机为基础,实现了一个简单的计算机声图系统。该系统的图形软件采用在KX-600图形显示系统上实现的MGP二维军用图形包,实现了语音输入的透明键盘支持。本文还提出了用自然语言输入和GKD-PROGKS图形系统构造的智能计算机图形系统的功能模型。A model of computer speech-graphics system is proposed in this paper. The paper describes its principle and its design mothod, and a simple computer speech-graphics system based on this mothod is developed. It consists of a TI-SPEECH speech processing system, a KX-600 graphics display system and an IBM-PC/AT computer. The graphics software package is MGP 2D military graphics package which is implemented in KX-600 graphics display system. It possesses the Transparent keyboard ability to support speech input. Finally, the paper proposes an intelligent computer graphics display model which consists of speech input, and GKD-PROGKS graphics system. It provides some valuable recommendations for the development of intelligent computer graphics display system.

关 键 词：语言信号处理 声图系统 微机 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]