数字0-9的语音识别实现，采用双门限端点检测算法，mfcc和lpcc相结合的特征参数提取，识别率较高。-Numbers 0-9 of speech recognition, adopts double threshold endpoint detection algorithm, the combination of MFCC and LPCC feature parameter extraction, the recognition rate is higher.

解决了连续马尔科夫模型训练、观测向量概率计算、输出参数估计问题，需安装HMM工具包-CHMM model,trianing and estimation

隐马尔可夫连续和离散情况下的MATLAB实现(MATLAB Realization of Hidden Markov Continuous and Discrete Conditions)