语音识别中的mfcc参数提取程序，从HTK中剪出来的，结果和HTK得出来的一模一样（配置文件已给）。39维的，带能量。-mfcc extraction process.Come from the HTK

GMM-EX gmm语音转换模型，以及里面详细的ex聚类程序介绍-GMM-EX GMM voice switching model, and the EX clustering, there are detailed introduced program

A robust speech recognit ion system based on discriminative learning of environmental features is proposed for recognit ion of environmental features in high noise background, and a g radient descent algo􀀂 rithm was adopted for parameter