MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
This addresses music generation for creative applications, offering a novel CNN-based approach in a domain dominated by RNNs, though it is incremental as it builds on existing GAN and conditional mechanisms.
The authors tackled symbolic-domain music generation by proposing MidiNet, a convolutional generative adversarial network that generates melodies one bar at a time, with results from a user study showing it performs comparably to MelodyRNN in realism and pleasantness but is reported as much more interesting.
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.