This chapter proposes the utilization of expert systems such as deep neural networks for bioacoustics classification and detection with continuous wavelet transform features. Acoustic monitoring through bioacoustics and machine learning research has gained considerable attention from the scientific community since both tools may provide great help in constructing automatic systems that are able to identify and catalog acoustic recordings. These means help us reach faster analysis tools that can filter and identify target signals. This is an exciting task in bird bioacoustics, where biologists are given the difficult task of listening to the signal of interest and identifying bird species, for instance, but in other contexts, different acoustic signals might be of interest. There is an increasing number of electronically based devices to capture audio data, equipped with multiple microphones and capable of operating in several kinds of environments. Monitoring and processing these recordings have become more complex, especially in the acoustic domain. Acoustic alarms against wildfires or intrusive species, bioindicator extraction, monitoring of vocal animals, including whales and dolphins, undersea analysis, observation and conservation of birds of interest over cities, estimating populations using audio data, insect diversity and biodiversity estimation, and selective capture of wildlife calls are a few examples of ecological and applied science problems that are highly time-consuming. In addition, acoustic detection has an important role in urban and rural areas to prevent possible natural disasters. The chapter protocol aims to contribute to a quick, accurate, and reliable automated bioacoustic event classifier, primarily focusing on the identification of birds that are present in a given captured audio query.