DeepAI AI Chat
Log In Sign Up

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

by   Li-Chia Yang, et al.
Academia Sinica

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.


page 1

page 2

page 3

page 4


MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment

Generating music has a few notable differences from generating images an...

Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network

Research on automatic music generation has seen great progress due to th...

Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization

In a recent paper, we have presented a generative adversarial network (G...

GANkyoku: a Generative Adversarial Network for Shakuhachi Music

A common approach to generating symbolic music using neural networks inv...

A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset

This paper proposes a new benchmark task for generat-ing musical passage...

Wykorzystanie sztucznej inteligencji do generowania treści muzycznych

This thesis is presenting a method for generating short musical phrases ...

Modeling Musical Onset Probabilities via Neural Distribution Learning

Musical onset detection can be formulated as a time-to-event (TTE) or ti...

Code Repositories


Generative adversarial network architecture that generates music in MIDI format.

view repo