作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (2): 200-202. doi: 10.3969/j.issn.1000-3428.2009.02.070

• 人工智能及识别技术 • 上一篇    下一篇

基于HMM的嵌入式语音交互在AmI中的应用

龚晓庆1,柯素娟2,李 辉2,华庆一1   

  1. (1. 西北大学信息科学与技术学院,西安 710069;2. 北京工业大学嵌入式软件与系统研究所,北京 100022)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-01-20 发布日期:2009-01-20

Application of Embedded Speech Interaction Based on HMM in AmI

GONG Xiao-qing1, KE Su-juan2, LI Hui2, HUA Qing-yi1   

  1. (1. College of Information Science and Technology, Northwest University, Xi’an 710069; 2. Institute of Embedded Software and Systems, Beijing University of Technology, Beijing 100022)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-01-20 Published:2009-01-20

摘要: 环绕智能的一个重要目的是实现人与环境的交互更加自然。该文通过语音识别技术体现环绕智能环境中的自然交互的理念,系统采用隐马尔可夫模型实现语音识别,同时为了保证嵌入式环境下交互的实时性,采用IP核来设计与实现算法,并进行仿真验证。实验数据表明系统具有较好的性能,对语音识别在环绕智能环境中的应用研究有一定的理论和实践意义。

关键词: 环绕智能, 语音识别, 嵌入式, 隐马尔可夫模型, IP核

Abstract: One of the main aims of Ambient Intelligence(AmI) is to make human interaction with the environment more natural. The concept of natural human machine interaction in AmI is embodied through speech recognition technology. In order to ensure the real-time of the interaction, the system implements the algorithms by using IP core technology. The experimental result shows that the system performs well and it is helpful for the application research of speech recognition technology in AmI.

Key words: Ambient Intelligence(AmI), speech recognition, embedded, Hidden Markov Model(HMM), IP core

中图分类号: