MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation

TL;DR

MidiNet is a novel CNN-based GAN model for symbolic music generation that can produce realistic, interesting melodies conditioned on prior musical context, outperforming some existing models in listener engagement.

Contribution

This paper introduces MidiNet, a CNN-based GAN for symbolic music generation with a novel conditioning mechanism and multi-channel expansion capabilities.

Findings

MidiNet generates melodies comparable to Google's MelodyRNN in realism.

Listeners find MidiNet's melodies more interesting than those from MelodyRNN.

MidiNet effectively conditions on prior melodies and chord sequences.

Abstract

Most existing neural network models for music generation use recurrent neural networks. However, the recent WaveNet model proposed by DeepMind shows that convolutional neural networks (CNNs) can also generate realistic musical waveforms in the audio domain. Following this light, we investigate using CNNs for generating melody (a series of MIDI notes) one bar after another in the symbolic domain. In addition to the generator, we use a discriminator to learn the distributions of melodies, making it a generative adversarial network (GAN). Moreover, we propose a novel conditional mechanism to exploit available prior knowledge, so that the model can generate melodies either from scratch, by following a chord sequence, or by conditioning on the melody of previous bars (e.g. a priming melody), among other possibilities. The resulting model, named MidiNet, can be expanded to generate music with multiple MIDI channels (i.e. tracks). We conduct a user study to compare the melody of eight-bar long generated by MidiNet and by Google's MelodyRNN models, each time using the same priming melody. Result shows that MidiNet performs comparably with MelodyRNN models in being realistic and pleasant to listen to, yet MidiNet's melodies are reported to be much more interesting.