Application-Programming Interface (API) for Song Recognition Systems

The main contribution of this paper is the framework of Application Programming Interface (API) to be integrated on a smartphone app. The integration with algorithm that generates fingerprints from the method ST-PSD with several parameter configurations (Windows size, threshold, and sub-score linear combination coefficient). An approach capable of recognizing an audio piece of music with an accuracy equal to 90% was further tested based on this result. In addition the implementation is done by algorithm using Java's programming language, executed through an application developed in the Android operating system. Also, capturing the audio from the smartphone, which is subsequently compared with fingerprints, those present in a database.