Automatic Bird Species Audio Detection

Abstract

Birds have been long monitored manually, which is very labor intensive. This work tries to explore and compare different types of neural networks (MLP,CNN,RNN,CRNN) to automatically find and classify acoustic activity of birds within audio recordings of wilderness. It could save a lot of time and effort, since people wouldn't have to go through the recordings and manually identify the birds. By saving lots of time, bird monitoring could be done at greater scale, helping with conservation and scientific research. The objective is to build a user-friendly application, where the user can train a new bird- identifying model and use it without needing any computer skills. 1