A study on underwater target recognition applying auditory slow feature analysis

Human listeners are capable of segregating and recognizing the class of signal better than machine recognizer in complex noisy conditions. In this paper, we proposed a novel approach for underwater target recognition applying auditory slow feature analysis (ASFA) based on gammatone (GT) filter and slow feature analysis. Our experimental evaluations show that the ASFA feature was proved to be considerably better than conventional acoustic features (i.e. Mel-frequency cepstral coefficients, MFCC). Moreover, the proposed ASFA feature is used for underwater target recognition system to yield promising recognition performance.