摘要
建立了一个基于HMM算法的非特定人语音识别系统,阐述了具体实现过程,包括预处理、特征参数的提取及模板的匹配。并用MATLAB6.5对整个系统进行了仿真,仿真结果表明该系统可实现对非特定人输入命令词的识别,识别率约为88.6%。
This paper has established a speaker-independent speech recognition system based on HMM algorithm. It also introduces its realization course including the pretreatment, the characteristic parametric extracting, and the template matching. Besides, the system is simulated using the MATLAB6.5 software. The simulation results indicate that this system can implement the speaker-independent command recognition and the recognition rate is about 88.6%.
出处
《湖南科技学院学报》
2009年第4期63-64,共2页
Journal of Hunan University of Science and Engineering
