This paper presents a framework to create new music using generative deep learning. Specifically, to create Western classical piano music based on music from Bach, Schubert, Chopin, and other famous composers. The core idea introduced is to use advanced Variational Autoencoders (VAE), Diffusion Models, and Generative Adversarial Networks (GAN) and combine them to create a better-performing model capable of generating classical piano music finetuned to the specific composers. The proposed ensemble methodology involves initial separate pretraining of a Variational Autoencoder (VAE) and a Generative Adversarial Network (GAN) on the dataset. Subsequently, the VAE encoder is utilized to establish a latent space, which undergoes refinement via a Diffusion Model. This refined latent space is then employed by the generator component, previously trained within the GAN framework, to generate novel music compositions adhering to the stylistic characteristics associated with specific music composers.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unified Framework for Classical Music Generation Using GANs, VAEs, and Diffusion




    Publication date :

    2024-12-05


    Size :

    302279 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Comparative Study on GANs and VAEs in Credit Card Fraud Detection

    Sukruth, S / Haripriya, Mc / Deepa, S et al. | IEEE | 2024


    f-VAEs: Improve VAEs with Conditional Flows

    Su, Jianlin / Wu, Guang | ArXiv | 2018

    Free access

    LEARNING HIERARCHICAL PRIORS IN VAES

    Klushyn, Alexej / Chen, Nutan / Kurle, Richard et al. | TIBKAT | 2020


    Relaxed-Responsibility Hierarchical Discrete VAEs

    Willetts, Matthew / Miscouridou, Xenia / Roberts, Stephen et al. | ArXiv | 2020

    Free access

    Character Controllers Using Motion VAEs

    Ling, Hung Yu / Zinno, Fabio / Cheng, George et al. | ArXiv | 2021

    Free access