Prof designs AI music software to generate 'bandish' of raga

A Pune-based academician has designed a software, which can generate 'bandish' of ragas in Indian classical music using Artificial Intelligence (AI).

Professor Vinod Vidwans, a PhD in Cognitive Philosophy from IIT Bombay, who has developed this software, said he has coded the concepts and composition rules of Indian classical music to generate a 'bandish' (composition) every time the vadi (dominant) and samvadi (sub dominant) swaras are provided as inputs.

Claiming that this is a first in the Indian classical music scene, he said his research explores the possibility of 'computer-created' Indian music or computational Indian music using AI.

"Advances in computers and new media technology have opened up new avenues for music-making. Many musical minds are already exploring these advances and looking forward to new horizons," Vidwans, former Chair, Faculty of Fine and Performing Arts at the FLAME University, said.

"The principles, concepts and conventional knowledge base of Indian music have been encoded in this system in the form of generic rules to generate music," he said.

According to him, his research has led to the generation of a 'bandish' on its own without any human assistance.

"The AI system has been tested with a number of ragas, including Hamsadhwani, Dhanashri, Malkaunsa, Maru Bihag and Bhairavi. This system possesses the knowledge of an expert in the domain of Indian classical music," he said.

"It is a rule-based expert system and does not have any database of ragas. On the contrary, it generates the required musical data following the rules. This is the 'generative' strength of AI," he said.

"If you provide aroha (ascending order of notes) and avaroha (descending order of notes) along with vadi and samvadi notes of the raga to the software, it generates the composition in a flash," he said.

It can be a useful tool to learn music and understand these rules with the help of a text file. It can also be useful for researchers in musicology for testing existing theoretical concepts in Indian music.

He said the software is also capable of generating novel musical phrases appropriate for a specific raga while rendering, so it is useful for experienced musicians to use it as a supplementary tool for practice.

For common listeners, the system will come in handy to generate a new composition every time they want to listen to a specific raga.

He said this AI system presently generates compositions in the artificially created instruments which produce flute-like sound, shahanai/ violin, sarod, string instrument and artificial sound of tanpura.