Study of speaker recognition based on improved feature parameter fusion

In this paper, a improved method based on speech feature parameter fusion(CCAFF) is proposed. First of all, Mel Frequency Cepstral Coefficients( MFCC), Linear Prediction Cepstrum Coefficient(LPCC )and accelerated coefficient are adopted as feature parameter and then Principle Component Analysis (PCA) are used to reduce the dimensionalities of the original feature vector space, at last, canonical correlation analysis is adopted to fusion these features. The results show that this method can efficiently accelerate the recognition capacity of the system, and the recognition results are better than those of using on kind of feature combination.