Combining dynamic features with MFCC for text-independent speaker identification

This paper presents text-independent speaker identification scheme based on the combination of dynamic features with Mel Frequency Cepstral Coefficients (MFCC). First, MFCCs are used to extract the speaker specific features and then vector quantization is used to model the speaker. We compare the performance of speaker identification system using number of MFCC filters and centroids of vector quantization. In addition, we also compare the effect of possible combinations of MFCC with log energy, delta and double delta coefficients for number of filters and centroids of vector quantization on recognition rate. The experimental results have been evaluated on the developed database of 75 speakers.