This paper discusses a modeling method of Minimum Variance Distortionless Response(MVDR)，which compares with the linear predictive method. The result is that the Minimum Variance Distortionless Response filter can afford better original speech envelope. On the basis of studying ICA and FastICA, the MVDR parameter pickingup method is combined with independent component analysis, which compares with the  traditional speech recognition under the conditions with noise and without noise, and the data are analyzed. The MVDR parameter pickingup method can improve the distinguishing rate of the speech recognition system, but increases the mean recognition time；and the speech recognition system with the ICA characteristic transform is more robust.