Acoustic Pattern Recognition on Android Devices

Ever since smartphones reached the general public, developers have been exploring the vast opportunities they provide. With their increasing number of sensors and processing power, we have now reached a point where the phones can collect and process large amounts of data. In this paper we present an Android application developed for acoustic pattern recognition of bird species. The acoustic data is recorded using a built-in microphone, and pattern recognition is performed on the device, requiring no network connection. The algorithm is implemented in C++ as a native Android module and the OpenCV library is used for signal processing. We conclude that the approach presented here is a viable solution to pattern recognition problems. Since it requires no network connection, it shows promise in fields such as wildlife research.