Music Generation Using Neural Networks

Sequence learning is attracting more and more attention both in industry and academic world with the wide usage of RNN and LSTM neural network architecture. Early this year, Google Brain team open sourced a research project named Magenta, which tries to provide a platform for musicians, artists and programmers to create their music and art works using machine intelligence. Several months later, DeepMind published their WaveNet paper which proposes a deep generative model of raw audio waveforms and achieves astonishing state of the art performance gain. In this paper, we are trying to explore potential solutions to marry the merits of these two projects and create a better model for music generation. We also conduct experiments to compare the performances and advantages of Magenta’s model, DeepMind’s model and another model named Biaxial-RNN.