Improved wavelet feature extraction using kernel analysis for text independent speaker recognition

摘要

A text independent speaker recognition system based on improved wavelet transform is proposed. Learning of the correlation between the wavelet transform and the expression vector is performed by kernel canonical correlation analysis. Kernel canonical correlation analysis is a nonlinear extension of canonical correlation analysis. Moreover, we also propose an improved kernel canonical correlation algorithm to tackle the singularity problem of the wavelet matrix. The identification model underlying the Gaussian mixture model is presented; in particular, an expectation-maximization algorithm is also proposed for adjusting the parameters. The experimental results on the TALUNG database and KING database illustrate the effectiveness of the proposed method.