Comparative Study of the Working of Various AI Classifiers for Identifying Ragas of Indian Classical Music

Music is an art of melody and sound. Classical music provides a framework for creating melodies and musical compositions. The most popular methods are Western classical music and Indian Classical Music (ICM). In ICM, the melodic pattern is called a Raga. Each Raga is classified based on the notes present, the order of the notes and the emotion (Rasa). Identifying a Raga is necessary for various music analyses. The objective of this research paper is to conduct a Systematic Literature Review (SLR) specifically to compare the working and performance of all the classifiers used in AI models proposed in previous research. The work involves a systematic literature review and a meta-analysis of all the AI classifier models used in ICM Raga Identification. The purpose of this study is to provide knowledge of the best performing AI classifier in Raga identification of ICM. The detailed analysis indicates that the model using Time Delay Neural Network (TDNN) displays the best performance over a large data set. This classifier can be considered for all further studies involving Raga identification which still in its nascent stage of research.