摘要
为了解决火车站售票系统处理售票业务效率低、速度慢和低智能化等问题,提出了一种基于HTK(HMM Tool Kit,隐马尔科夫模型工具箱)的汉语语音售票系统。详细阐述了基于HTK的语音识别等关键技术的基本原理,并给出了系统实现的关键代码。在语音识别测试中,语句级识别正确率为98.00%;字词级识别正确率达到了98.67%。实验结果表明所提出的语音售票系统具有较高的可行性与实用性。
To solve some problems,such as low- efficiency,low-speed and low-intelligence,which exist in the station ticketing sys- tem,a Chinese speech ticketing system based on HTK is presented in this paper.Some basic principles of key speech recognition technologies and key program codes are described.Experiential results reveal that the recognition ratio of state- ment-level is 98.00% and that of word-level reaches 98.67% in the proposed speech recognition system,which show that the proposed system has a high feasibility and practicality.
出处
《工业控制计算机》
2010年第10期58-61,共4页
Industrial Control Computer
关键词
语音识别
HTK
售票系统
ATK
speech recognition
HTK（HMM Tool Kit）
ticketing system
ATK（An Application Toolkit for HTK）
