ClaviNet: Generate music with different musical styles
Document Type
Article
Publication Date
1-1-2021
Abstract
Classically, the style of the generated music by deep learning models is usually governed by the training dataset. In this article, we improved this by proposing the continuous style embedding ${z}_{s}$zs to the general formulation of variational autoencoder (VAE) to allow users to be able to condition on the style of the generated music. For this purpose, we explored and compared two different methods to integrate z(s) into the VAE. In the literature of conditional generative modeling, disentanglement of attributes from the latent space is often associated with better generative performance. In our experiments, we find that this is not the case with our proposed model. Empirically and from a musical theory perspective, we show that our proposed model can generate better music samples than a baseline model that utilizes a discrete style label. The source code and generated samples are available at .
Keywords
Music, Training, Computer generated music, Decoding, Task analysis, Instruments, Context modeling, Music synthesis, Deep learning, Style transfer
Divisions
fsktm
Funders
None
Publication Title
IEEE Multimedia
Volume
28
Issue
1
Publisher
IEEE Computer Soc
Publisher Location
10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1314 USA