Крюкова, ГалинаСавкін, Гліб2024-11-012024-11-012024https://ekmair.ukma.edu.ua/handle/123456789/32124In this work, we aim to research the possibility of applications of diffusion models for the task of symbolic audio generation. We will implement and train a diffusion model, comparing its performance against other popular models for music generation. By providing results and analysis, this study aims to demonstrate the advantages of DDPMs for music generation and to create a foundation for future research in the use of generative models in music generation.enDenoising Diffusion Probabilistic Models (DDPMs)Variational AutoEncoders (VAEs)Generative Adversarial Networks (GANs)Transformer-Based Modelsbachelor thesisOther