Music Classification and Identification System

We have implemented a system to recognize and classify music. Given an audio sample; our system is able to determine the genre, artist, album, and title of the given song. This is done by creating a database of models based on songs it’s trained on. Input songs’ features and models are compared with existing models to determine the identity of the song, along with its genre, artist, and album. This system is robust enough to handle thousands of songs, and allows for classification of any number of input samples. Since the system is classifying songs on an acoustic level, it is immune to small amounts of noise, added silence, and encoding rate of the input sample.