Application of fast learning neural-networks to identification of mixed anuran vocalizations

Abstract

The proposed identification system for mixed anuran vocalizations is to provide the public to easily consult online. The raw mixed anuran vocalization samples are first filtered by noise removal, high frequency compensation, and discrete wavelet transform techniques in order. An adaptive end-point detection segmentation algorithm is proposed to effectively separate the individual syllables from the noise. Six features, including spectral centroid, signal bandwidth, spectral roll-off, threshold-crossing rate, spectral flatness, and average energy, are extracted and serve as the input parameters of wrapper feature selection method. Meanwhile, a decision tree is constructed based on several parameters obtained during sample collection in order to narrow the scope of identification targets. Then fast learning neural-networks are employed to classify the anuran species. Experimental results exhibit that the recognition rate of the proposed identification system can achieve up to 93.3%. The effectiveness of the proposed identification system for anuran vocalizations is thus verified.