Analytical Comparison of Classification Models for Raga Identification in Carnatic Classical Audio

Abstract

There is this famous quote which goes as follows “MUSIC is the divine way of portraying the most beautiful things about this world.” With that being said, the diversity in this language of music is immense, to say the least. Broadly, one would be well aware of the classification between Indian classical music and western music. In music information retrieval (MIR), raga classification has a tremendous part role in understanding the fundamentals of Indian classical music and in a multitude of other tasks like database organization of music files to music recommendation systems. The paper encompasses a variety of techniques like ANN, LSTM, and XGBoost models for the task of raga identification. The work is initially carried out on a set of 10 ragas and then extended to 20 ragas. Both the tasks showed impressive results with an accuracy of 99.56% and 99.43% for a set of ten and twenty ragas, respectively. The process was carried out on the ragas pertaining to Carnatic music, a division of Indian classical music. The data samples for the same were obtained from a standard data set.