In a recent paper posted on the arXiv preprint server, researcher Marco Pasini and his colleagues Stefan Lattner and Maarten Grachten at Sony CSL, introduced a new latent diffusion model that can create realistic and effective bass accompaniments for musical tracks. Diffusion models are deep learning techniques that can learn to generate images, audio or other samples that capture the overall structure underlying a dataset.
Source: The AI bassist: Sony’s vision for a new paradigm in music production