C-RNN-GAN: Continuous recurrent neural networks with adversarial training
This work addresses the challenge of generating realistic sequential data like music for applications in creative AI, though it appears incremental as it adapts existing GAN methods to a new data type.
The authors tackled the problem of generating continuous sequential data, specifically classical music, using a generative adversarial network (GAN) combined with continuous recurrent neural networks (C-RNN-GAN), resulting in generated music that improves in quality with training and includes reported statistics for evaluation.
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.