Speaker recognition based on principal component analysis of LPCC and MFCC

This paper introduces a new method of extracting mixed characteristic parameters using the principal component analysis (PCA), this method proposed is based on widely use of the PCA and K-means clustering in image and speech signal processing. The first work is systematic study of extracting algorithm and theory for speaker recognition system, which is on the most commonly used LPCC (Linear Prediction Cepstrum Coefficient), MFCC (Mel Frequency Cepstrum Coefficient) and differential parameter. Therefore, we select combination of the LPCC, MFCC and the first-order differential parameter as the characteristic parameter. After calculating by means of PCA, the characteristic parameter reduce the orders of each frame of speech signal, and then reduce the frame numbers through the K-means clustering , finally recognizing speaker by VQ. The experimental results show that, this method not only reduces the computational complexity, but also increases correct recognition rate.