Fork me on GitHub

C-RNN-GAN: Continuous recurrent neural networks with adversarial training

C-RNN-GAN

Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and let the reader judge the quality by downloading the generated songs.

Generated music samples

sample11.mp3
sample09.mp3

More samples of generated music can be downloaded from https://github.com/olofmogren/c-rnn-gan-samples/.

Source code

The source code used for the experiments can be downloaded from https://github.com/olofmogren/c-rnn-gan/.

Olof Mogren

Constructive Machine Learning Workshop (CML) at NIPS 2016 in Barcelona, Spain, December 10.
PDF Fulltext bibtex.

Olof Mogren, Department of Computer Science and Engineering, Chalmers University of Technology

LinkedIn Twitter Atom/RSS Feed