Fusion of Linear and Mel Frequency Cepstral Coefficients for Automatic Classification of Reptiles

Abstract

Bioacoustic research of reptile calls and vocalizations has been limited due to the general consideration that they are voiceless. However, several species of geckos, turtles, and crocodiles are abletoproducesimpleandevencomplexvocalizationswhicharespecies-specific.Thisworkpresents a novel approach for the automatic taxonomic identification of reptiles through their bioacoustics by applying pattern recognition techniques. The sound signals are automatically segmented, extracting each call from the background noise. Then, their calls are parametrized using Linear and Mel Frequency Cepstral Coefficients (LFCC and MFCC) to serve as features in the classification stage. In this study, 27 reptile species have been successfully identified using two machine learning algorithms: K-Nearest Neighbors (kNN) and Support Vector Machine (SVM). Experimental results show an average classification accuracy of 97.78% and 98.51%, respectively.

Keywords

• biological acoustic analysis
• bioacoustic taxonomy identification
• reptile vocalization
• frequency cepstral coefficients
• SVM
• kNN