Sankalp Gulati will present the paper titled “Phrase-based rāga recognition using vector space modeling,” which I am one of the co-authors of, in the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 in Shanghai, China.

The paper (PDF), proposes a novel methodology for rāga recognition based on mining melodic motifs. The method has been compared with my pitch distribution based recognition methodology published in Computer Music Journal (PDF) in 2013. We used morty (GitHub), an open source toolbox implementing this method.

Organized by IEEE, ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications.