The Matrix profile for motif discovery in audio - an example application in Carnatic music

Abstract

We present here a pipeline for the automated discovery of repeated motifs in audio. Our approach relies on state-of-the-art source separation, pre- dominant pitch extraction and time series motif detection via the matrix profile. Owing to the appropriateness of this approach for the task of motif recognition in the Carnatic musical style of South India, and with access to the recently re- leased Saraga Dataset of Indian Art Music, we provide an example application on a recording of a performance in the Carnatic r ̄aga, R ̄itigaul.a, finding 56 dis- tinct patterns of varying lengths that occur at least 3 times in the recording. The authors include a discussion of the potential musicological significance of this motif finding approach in relation to the particular tradition and beyond.