Usually, speaker recognition systems do not take into account the short–term dependence between the vocal source and the vocal tract. A feasibility study that retains this dependence is presented here. A model of joint probability functions of the pi

gmm模型训练程序，说话人识别系统中基于GMM的说话人识别方法中，对特征参数进行模型训练的函数-gmm model training program, speech recognition system GMM speaker recognition method based on the characteristic parameters of the model training function

基于gmm的语音识别系统，进行声纹识别，数据样例也有-Speech recognition system based on GMM

Speech - Emotion Recognition - Large-Margin GMM - IEEE 2012