Bird sounds classification by large scale acoustic features and extreme learning machine

Automatically classifying bird species by their sound signals is of crucial relevance for the research of ornithologists and ecologists. In this study, we present a novel framework for bird sounds classification from audio recordings. Firstly, the p-centre is used to detect the 'syllables' of bird songs, which are the units for the recognition task; then, we use our openSMILE toolkit to extract large scales of acoustic features from chunked units of analysis (the 'syllables'). ReliefF helps to reduce the dimension of the feature space. Lastly, an Extreme Learning Machine (ELM) serves for decision making. Results demonstrate that our system can achieve an excellent and robust performance scalable to different numbers of species (mean unweighted average recall of 93.82%, 89.56%, 85.30%, and 83.12% corresponding to 20, 30, 40, and 50 species of birds, respectively).