Generation of Indian Classical Music using Artificial Intelligence: A Survey

Bharavi U. Desai, Kunjal I. Tandel, Rahul M. Patel

Abstract: This paper is a survey and an examination of the various ways in which classical music content is produced. For our survey, we propose a framework focused on five dimensions: Objective, Representation, Architecture, Challenge and strategy. For each dimension, we conduct a comparative analysis of various models and techniques and we propose some tentative multidimensional typology. This typology is bottom-up, based on the analysis of many existing deep-learning based systems for music generation selected from the relevant literature.

Keywords: LSTM, GRU, RNN, Arohana, Avrohana, FSM, Gamakas, HMM