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.

[1]  Pedro J. Moreno,et al.  A Study of Musical Instrument Classification Using Gaussian Mixture Models and Support Vector Machines , 1999 .

[2]  Steve Lawrence,et al.  Artist detection in music with Minnowmatch , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[3]  Frédéric Bimbot,et al.  Experiments on speech tracking in audio documents using Gaussian mixture modeling , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[4]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.