Robust underwater target recognition using auditory cepstral coefficients

Abstract

Feature vector extraction is measured as major step in development of underwater target recognition. To improve robustness of the performance of feature vector extraction, we proposed a novel approach for robust underwater target recognition applying the auditory cepstral coefficients (ACC) based on auditory filter and cubic-log compression instead of Mel filter and logarithmic compression in Mel-frequency cepstral coefficients (MFCC). Our experimental results show that the ACC feature represents considerably better than conventional acoustic features, and the ACC feature is used for underwater target recognition system to yield promising recognition performance.