Deep generative models for musical audio synthesis
This is an incremental review that synthesizes existing developments in deep learning for audio synthesis, aimed at researchers and practitioners in sound modelling.
The paper reviews how deep generative models are transforming sound modelling by learning to generate audio from data and enabling new control strategies, moving beyond traditional labor-intensive methods.
Sound modelling is the process of developing algorithms that generate sound under parametric control. There are a few distinct approaches that have been developed historically including modelling the physics of sound production and propagation, assembling signal generating and processing elements to capture acoustic features, and manipulating collections of recorded audio samples. While each of these approaches has been able to achieve high-quality synthesis and interaction for specific applications, they are all labour-intensive and each comes with its own challenges for designing arbitrary control strategies. Recent generative deep learning systems for audio synthesis are able to learn models that can traverse arbitrary spaces of sound defined by the data they train on. Furthermore, machine learning systems are providing new techniques for designing control and navigation strategies for these models. This paper is a review of developments in deep learning that are changing the practice of sound modelling.