摘要 : 在 MAT LAB环境下利用语音工具箱 Voice Box实现基于连续概率密度隐含马尔科夫模型的汉语语音识别系统。在

实时录音的情况下 , 利用该语音识别系统 , 不同的人对 20条 2～8个字的语音命令进行识别 , 准确率可达到 95 ％ , 识别时间

115～3 s , 实现了小词汇量连续语音的非特定人的实时识别。-Abstract: In the circumstances the use of MAT LAB toolbox Voice Box Voice realize implied probability density based on continuous Markov model of Chinese speech recognition system. In real-time recording, the use of the voice recognition systems, different people on the 20 2 ~ 8-word voice command recognition accuracy rate can reach 95 percent, identify the time 115 ~ 3 s, the realization of a small vocabulary continuous voice of the non-specific real-time identification of people.