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

Abstract

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.

On the Development and Practice of AI Technology for Contemporary Popular Music Production

“…BassNet, LeadNet: Tools for creating bass tracks (BassNet) or lead tracks (LeadNet), conditioned on one or more existing audio tracks (Grachten et al, 2020). The output adapts to the tonality of the existing tracks (if the input is tonal), and users can explore different rhythmic and melodic variations of the output by traversing a latent space.…”

“…The priming input can be used in diferent ways: it can serve as the start of a musical part to be continued by the tool, as the starting template from which variations can be explored, or as a part in a multi-part setting for which the tool generates accompanying parts. Priming amounts to what is referred to as dense conditioning (Grachten et al, 2020), where the output of a model is controlled by providing a rich source of information (e.g. an audio or MIDI track) instead of sparser types of information that are provided by the typical UI elements of a control panel (sliders, buttons, presets, etc.).…”

Applications of Computational Intelligence in Computer Music Composition

“…K. Komatasu et al [35] system is another example of a bass-line generation model through genetic programming. BassNet [36] is a recently developed Bass Guitar tracks generator that utilize deep learning. This system is a conditional generator based on a given input musical pieces rather than generating from scratch.…”

Special Issue on Deep Learning for Applications in Acoustics: Modeling, Synthesis, and Listening

“…Several papers in this special issue deal with music-related tasks such as the generation of bass scores [7], chord progressions [8], and the analysis of rhythmic patterns [9].…”

“…Grachten et al [7] present a variational gated auto-encoder model for conditional generation of bass notes. They focus on temporally stable and controllable sequence generation, which is critical in human-collaborative music creation.…”