MG-VAE: Deep Chinese Folk Songs Generation with Specific Regional Style
This work addresses the need for ethnic music creation and folk culture research by enabling deep generative modeling for Chinese folk songs, though it is incremental as it builds on existing VAE and adversarial techniques.
The authors tackled the problem of generating Chinese folk songs with controllable regional styles by proposing MG-VAE, a VAE-based model that disentangles latent space into pitch, rhythm, style, and content components using adversarial training, resulting in successful disentanglement and the ability to create novel, style-controllable tunes.
Regional style in Chinese folk songs is a rich treasure that can be used for ethnic music creation and folk culture research. In this paper, we propose MG-VAE, a music generative model based on VAE (Variational Auto-Encoder) that is capable of capturing specific music style and generating novel tunes for Chinese folk songs (Min Ge) in a manipulatable way. Specifically, we disentangle the latent space of VAE into four parts in an adversarial training way to control the information of pitch and rhythm sequence, as well as of music style and content. In detail, two classifiers are used to separate style and content latent space, and temporal supervision is utilized to disentangle the pitch and rhythm sequence. The experimental results show that the disentanglement is successful and our model is able to create novel folk songs with controllable regional styles. To our best knowledge, this is the first study on applying deep generative model and adversarial training for Chinese music generation.