Music information retrieval rests heavily on the notion of musical similarity ideally modeled on human judgments of the same. Audio MIR techniques thus seek to bridge the gap between semantically useful music concepts and audio signal descriptions to benefit applications such as music recommendation, performance analyses, and music generation. A powerful source of knowledge for MIR is the vast body of musicology scholarship that informs the music of different cultures. We discuss how computational methods in turn help us obtain a deeper understanding of the theory and practice of a sophisticated oral musical tradition such as Indian raga music through audio analyses of performances.
Preeti Rao is on the faculty of Electrical Engineering at I.I.T. Bombay, teaching and researching in the area of signal processing with applications in speech and audio. She was a collaborator in the CompMusic project during 2011-2016 for the application of music information retrieval techniques to non-Western music. She currently leads another international collaboration funded by the Government of India for research in Computational Musicology and Musical Instruments Modeling for Indian Music. She has been actively involved in the development of technology for Indian music and spoken language learning applications.