A New Algorithm for Auditory Feature Extraction

The human auditory system possesses remarkable capabilities to analyze and identify signals. An auditory feature can improve the performance of speaker recognition system. In this paper, it used gammatone filter to model auditory system, and extracted a traditional auditory feature based on logarithmic energy. On the purpose to reduce the dimension of the traditional auditory feature which was always a high dimensional feature, we took use of discrete cosine transform (DCT). Therefore, it was feasible to apply auditory model extracted in a new way to speech feature extraction. The experiments showed that the GFCC feature, which was extracted in the new method, performed better than the traditional MFCC feature in the speaker recognition system based on GMM model.