An approach for analysis and identification of Raga of Flute Music using Spectrogram
M.N. Anoop, Turaga Deepak, T. Shreekanth · 2017 International Conference on Trends in Electronics and Informatics (ICEI) · 2017
This work presents an approach for identification of Raga of Flute music. Identification of Raga plays a vital role in learning about the rules in playing a composition, determining the valid Swaras, tunes and deflections. Experts can identify the Raga easily, learners cannot. The earlier works in this direction have dealt with Human Voice and simple Musical Instruments other than Flute, which could not address the versatility of source instrument or the Vocalist. In this work, application of Spectrogram for Raga analysis has been proposed which addresses the issues in the existing methods. The performance evaluation of the proposed method was evaluated on a database consisting of 32 Ragas using the statistical measures such as True Positive (TP), True Negative (TN), False Positive (FP) and False Negative (FN). The test consists of 40 samples with complete scale of each raga and obtained TP of 90%, FN of 0%, TN of 100% and FP of 10%. Hence, the Accuracy of the proposed method is 95%.