Learning Indian Classical Using Sequential Models

Team Members

• Dhananjay Kulkarni
• Tarun Kumar

Project Idea

Indian Classical music is a very structured when it comes to melody. A composition is (generally) within a constraints of a raag. It has a specific grammar, which lends the emotions to the composition. This aspect of music lends an interesting application of sequential models for note prediction, and raga classification.

Previous Work

Hidden Markov Models have been used for raga classification. The first step is to transcribe the music. This is either done by playing a midi keyboard, or if a performance is used, using frequency identification techniques. Such techniques are specified in [2].

Dataset

There are midi files available at http://www.cse.iitk.ac.in/users/tvp/music/.

References

1. http://www.slideshare.net/butest/music-and-machine-learning

2. TANSEN : A SYSTEM FOR AUTOMATIC RAGA IDENTIFICATION