Bird Voice Classification and Recognition Based on BA-ELM

As one of the indispensable biological groups in the earth's ecosystem, the determination of bird species plays a very important role in various aspects such as conservation of biodiversity and optimization of ecological balance. Bird calls are one of the most important features in bird biology, and the purpose of this paper is to extract features and successfully classify and identify bird sound signals. In this paper, Mel frequency cepstral coefficient is used for feature extraction and species labeling of 10 common bird sound signals around Shanghai, and an extreme learning machine optimized based on bat algorithm is used as a classifier to classify and identify bird features. The experimental results show that the recognition rate of the optimized extreme learning machine is 93%, which is more than 20% higher than that of the unoptimized one.