Predicting Gamaka s-The Essential Embellishments in Karnatic Music

• Published in: IEEE access 2019, Vol.7, p.175386-175395
• Main Authors: Rajan, M. Ragesh, Vijayasenan, Deepu, Vijayakumar, Ashwin
• Format: Article
• Language: English
• Subjects: <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">Gamaka; Feature extraction; Forestry; karnatic music; Music; note-based features; random forest classifier; symbolic music; Task analysis; Training; Training data
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2957236

Gamaka s are the musical embellishments used in Karnatic Music. Predicting them from the musical notations plays an important part in applications like automatic synthesis and composition of Karnatic Music. Since there are no well-defined rules governing the use of gamaka s, predicting them is a challenging problem. In this work, we propose a method to detect the presence and type of gamaka s, in a data-driven manner, from the annotated symbolic music alone. We propose features based on the notes of the song for these tasks. These features are used as inputs to a Random Forest Classifier. We digitise 80 songs from a well known reference book of Karnatic music to create a dataset consisting roughly 30000 notes. We train the classifier on around 12000 notes and test on roughly 18000 notes. From our experiments, the accuracy values obtained for predicting gamaka presence and type are ~77% and ~70%, respectively. These are significantly better than random classification accuracies. We also analyse the importance of neighbourhood of notes for the detection and classification of gamaka s. It is observed that the best accuracy is obtained for gamaka presence detection when a both-sided neighbourhood of size three is considered; and best accuracy for gamaka type prediction is obtained with a both-sided neighbourhood of size one. The analysis performed on the training data reveals that there is information contained in these neighbourhoods for distinguishing between gamaka and non- gamaka notes.