摘要
为了研究语音识别技术的实用化问题.采用离散隐马尔可夫模型方法,基于单片微控制器加数字信号处理器(MCU+DSP)构架,实现了一个非特定人语音指令识别系统.该系统适应性强,每个指令识别时间在1s内,准确率达到96%.
In order to research the problem of practical speech recognition, this paper introduces a solution of speaker-independent speech instructions recognition in embedded system which is based on MCU ＋ DSP architecture, it realizes the system by Hidden Markov Models（HMM） algorithm. After optimization, the system has a better performance in mandarin recognition.
出处
《哈尔滨理工大学学报》
CAS
2008年第2期75-77,81,共4页
Journal of Harbin University of Science and Technology
关键词
语音识别
非特定人
隐马尔可夫模型
speech recognition
speaker-independent
Hidden Markov Models
