Real-Time Raag Recognition for Interactive Music

Chordia, Parag and Rae, Alex

Proceedings of the International Conference on New Interfaces for Musical Expression

We describe a system that can listen to a performance of Indian music and recognize the raag, the fundamental melodicframework that Indian classical musicians improvise within.In addition to determining the most likely raag being performed, the system displays the estimated the likelihoodof each of the other possible raags, visualizing the changesover time. The system computes the pitch-class distributionand uses a Bayesian decision rule to classify the resultingtwelve dimensional feature vector, where each feature represents the relative use of each pitch class. We show that thesystem achieves high performance on a variety of sources,making it a viable tool for interactive performance.