Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model

Utilizing deep learning techniques to generate musical contents has caught wide attention in recent years. Within this context, this paper investigates a specific problem related to music generation, music style transfer. This practical problem aims to alter the style of a given music piece from one to another while preserving the essence of that piece, such as melody and chord progression. In particular, we discuss the style transfer of homophonic music, composed of a predominant melody part and an accompaniment part, where the latter is modified through Gibbs sampling on a generative model combining recurrent neural networks and autoregressive models. Both objective and subjective test experiment are performed to assess the performance of transferring the style of an arbitrary music piece having a homophonic texture into two different distinct styles, Bachs chorales and Jazz.