Evaluation of various feature sets and feature selection towards automatic recognition of bird species

Abstract

It is necessary to develop efficient methods for monitoring and recognising bird species that will help in evaluating the biodiversity of a region. In this paper we present techniques for automatic recognition of bird species based on audio recordings of their sounds. In this work, various audio features like descriptive features, wavelet packet decomposition-based features and perceptual features like Mel-frequency cepstral coefficients, perceptual linear prediction, and human factor cepstral coefficients are evaluated. Combination of these feature sets has also been evaluated. Classification of ten bird species is carried out using Gaussian Mixture Modelling (GMM) and Support Vector Machines (SVMs). When a number of features are extracted, the feature vector may contain redundancy. Redundant features may either degrade the performance of the system or add no value to the system. For feature subset selection, this work implements a technique based on singular value decomposition and QR decomposition using column pivoting.