Next Article in Journal
Continuance Use of Cloud Computing in Higher Education Institutions: A Conceptual Model
Next Article in Special Issue
Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform
Previous Article in Journal
Taylor Bird Swarm Algorithm Based on Deep Belief Network for Heart Disease Diagnosis
Previous Article in Special Issue
Assistive Model to Generate Chord Progressions Using Genetic Programming with Artificial Immune Properties
Open AccessArticle

BassNet: A Variational Gated Autoencoder for Conditional Generation of Bass Guitar Tracks with Learned Interactive Control

1
Contractor for Sony Computer Science Laboratories, 75005 Paris, France
2
Sony Computer Science Laboratories, 75005 Paris, France
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(18), 6627; https://doi.org/10.3390/app10186627
Received: 1 August 2020 / Revised: 31 August 2020 / Accepted: 17 September 2020 / Published: 22 September 2020
Deep learning has given AI-based methods for music creation a boost by over the past years. An important challenge in this field is to balance user control and autonomy in music generation systems. In this work, we present BassNet, a deep learning model for generating bass guitar tracks based on musical source material. An innovative aspect of our work is that the model is trained to learn a temporally stable two-dimensional latent space variable that offers interactive user control. We empirically show that the model can disentangle bass patterns that require sensitivity to harmony, instrument timbre, and rhythm. An ablation study reveals that this capability is because of the temporal stability constraint on latent space trajectories during training. We also demonstrate that models that are trained on pop/rock music learn a latent space that offers control over the diatonic characteristics of the output, among other things. Lastly, we present and discuss generated bass tracks for three different music fragments. The work that is presented here is a step toward the integration of AI-based technology in the workflow of musical content creators. View Full-Text
Keywords: music generation; deep learning; latent space models; user control music generation; deep learning; latent space models; user control
Show Figures

Figure 1

MDPI and ACS Style

Grachten, M.; Lattner, S.; Deruty, E. BassNet: A Variational Gated Autoencoder for Conditional Generation of Bass Guitar Tracks with Learned Interactive Control. Appl. Sci. 2020, 10, 6627. https://doi.org/10.3390/app10186627

AMA Style

Grachten M, Lattner S, Deruty E. BassNet: A Variational Gated Autoencoder for Conditional Generation of Bass Guitar Tracks with Learned Interactive Control. Applied Sciences. 2020; 10(18):6627. https://doi.org/10.3390/app10186627

Chicago/Turabian Style

Grachten, Maarten; Lattner, Stefan; Deruty, Emmanuel. 2020. "BassNet: A Variational Gated Autoencoder for Conditional Generation of Bass Guitar Tracks with Learned Interactive Control" Appl. Sci. 10, no. 18: 6627. https://doi.org/10.3390/app10186627

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop