Abstract: 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.