Folk music style modelling by recurrent neural networks with long short term memory units
Bob L. T. Sturm, João Felipe Santos, Iryna Korshunova · Ghent University Academic Bibliography (Ghent University) · 2015
We demonstrate two generative models created by training a recurrent neural network (RNN) with three hidden layers of long short-term memory (LSTM) units. This extends past work in numerous directions, including training deeper models with nearly 24,000 high-level transcriptions of folk tunes. We discuss our on-going work.