Study On Speaker Recognition System Based On Gaussian Mixture Model

Speaker recognition is a kind of biological certification technology and it makes use of the speech coefficients which represent the speaker's physiological and physical feature to identify speaker. In the biological certification area, speaker recognition widely draws the attention because of its convenience, efficiency and accuracy.This thesis studies the speaker recognition system with GMM (Gauss Mixture Model). On the basis of performance tests and comparison, the thesis modifies the modules of feature extraction, classification algorithm and recognition statistics to improve the recognition rate. The study work of this thesis has several aspects:(1) Constituting the integrated system:On the basis of speech segmentation and recognition rate calculation, the impact of different length of speech units on recognition rate is studied to verify the system correction and reliability.The tests on pre-emphasis coefficient and windowing frame length in pre-emphasis processing are made to get the best pre-emphasis coefficient and the best frame length in GMM with different orders.(2) Study on the capability of system:On the same test condition, the advantage and disadvantage of LPC, LPCC and MFCC features are studied. The results show that MFCC which sufficiently models the human hearing feature has a high performance on improving recognition rate.On the same test condition, the impact of the order of GMM on system recognition rate is studied. The negative impact of higher or lower order is analyzed, and the choice is made according to the practical circumstance.Setting covariance threshold in EM algorithm iteration is put forward. The comparison of experiments on different threshold is made, finding 0.10 is a universal and practical value for the covariance threshold.(3) Amelioration on the system:Improvement on basic feature MFCC is made and difference cepstrum is introduced. Different tests verify that the efficiency of considering the difference feature of adjacent frames.Consider that the conventional EM algorithm has the defect of singularity matrix, coefficient α is introduced to control the correction scaling in order to correct the result, and the efficiency of the improved algorithm on coefficient estimation is verified.