ISCA Archive SMM 2020
ISCA Archive SMM 2020

Grammar-constrained music generation for unconstrained doodling

Venkata S Viraraghavan, Vasundhara Agrawal, Rahul Dasharath Gavas, Tince Varghese, Varnika Naik, Mayuri Duggirala, Ramesh K Ramakrishnan

´╗┐Music as well as art both have been long recognized for their therapeutic benefits. Music not only helps in enhancing general wellbeing but also in combating several mental health issues. Similarly, art therapy enables individuals to cope with their emotional conflicts and allows self-expression. In art therapy, doodling has especially been recognized for its various benefits ranging from catharsis to improvement in memory. In this paper we propose a system that amalgamates music and doodling. The paper presents the mapping of the unconstrained doodling patterns received as user input to generate pleasant music using certain constraints. The paper explains the implementation of these constraints in the form of the musical grammar from the genre of Hindustani and Carnatic music. Initial feedback indicates that such genre-based constraints are clearly needed for the generated audio to sound musical.

doi: 10.21437/SMM.2020-2

Cite as: Viraraghavan, V.S., Agrawal, V., Gavas, R.D., Varghese, T., Naik, V., Duggirala, M., Ramakrishnan, R.K. (2020) Grammar-constrained music generation for unconstrained doodling. Proc. Workshop on Speech, Music and Mind (SMM 2020), 6-10, doi: 10.21437/SMM.2020-2

  author={Venkata S Viraraghavan and Vasundhara Agrawal and Rahul Dasharath Gavas and Tince Varghese and Varnika Naik and Mayuri Duggirala and Ramesh K Ramakrishnan},
  title={{Grammar-constrained music generation for unconstrained doodling}},
  booktitle={Proc. Workshop on Speech, Music and Mind (SMM 2020)},