ClaviNet: Generate music with different musical styles

Lim, Yu-Quan and Chan, Chee Seng and Loo, Fung Ying (2021) ClaviNet: Generate music with different musical styles. IEEE Multimedia, 28 (1). pp. 83-93. ISSN 1070-986X, DOI

Full text not available from this repository.


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 .

Item Type: Article
Funders: None
Uncontrolled Keywords: Music; Training; Computer generated music; Decoding; Task analysis; Instruments; Context modeling; Music synthesis; Deep learning; Style transfer
Subjects: M Music and Books on Music > M Music
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Ms Zaharah Ramly
Date Deposited: 04 Apr 2022 07:12
Last Modified: 04 Apr 2022 07:12

Actions (login required)

View Item View Item