Music generation with variational recurrent autoencoder supported by history

A serious problem for automated music generation is to propose the model that could reproduce sophisticated temporal and melodic patterns that would correspond to the style of the training input. We propose a new architecture of an artificial neural network that helps to deal with such tasks. The proposed approach is based on a long short-term memory language model combined with variational recurrent autoencoder. These methods have certain advantages when dealing with temporally rich inputs. The proposed architecture comprises this features and helps to generate results of higher complexity and diversity.