Real-Time Raag Recognition for Interactive Music

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