中文摘要：

特征参数的提取在说话人识别中起至关重要的作用,影响到整个系统的识别率.采用表征说话人语音特性的Mel倒谱系数和体现语音信号时域特征的短时TEO能量的混合特征参数应用到说话人识别系统中,目的是通过增加表征说话人语音特征参数的维数,来改善系统性能,与传统提取方法相比,该方法弥补了特征参数有效维数的不足,最后建立GMM-UBM分类器模型,对语音信号识别.实验证明,该混合特征参数与MFCC,以及MFCC与其一阶差分的组合特征参数相比,在没有增加运算复杂度的同时提高了系统的识别率.

英文摘要：

The extracting of characteristic parameters play a vital role in speaker recognition that affecting the recognition performance of the entire speaker recognition system.Mel Frequency Cepstral（MFCC）that reflecting individual voice characteristics and short-time TEO energy that reflecting time-domain characteristics of the speech signal mixed feature parameters was adopted to apply to the speaker recognition system,compared with traditional feature extraction methods,this method increases the effective dimension of features to improve the shortage of the characteristics sample.Then,the speaker recognition is based on GMM-UBM classification model.Experiments show that the improved characteristic parameter compared to MFCC and MFCC＋ΔMFCC,without increasing the computational complexity and improving the system recognition rate.