A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks

The paper describes a method that uses evolving LSTM recurrent neural networks to generate melodic music through a discriminative model. The approach enclosed has achieved an accuracy level of over 90%, thus enabling our model to understand & generate music as per the input parameters. The input expected from the user is minimal and can be provided by a layman. The experiments presented here demonstrate how LSTM can successfully learn a form of training music data and compose a novel (and pleasing) melody based on that style of training. LSTM can play melodies with good timing and appropriate structure if the parameters have been set appropriately. The RNN Model presented in this paper leverages the benefits of LSTM networks and demonstrates how this feat can be achieved.