English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Diffusion models have shown promising results for a wide range of generativetasks with continuous data, such as image and audio synthesis. However, littleprogress has been made on using diffusion models to generate discrete symbolicmusic because this new class of generative models are not well suited fordiscrete data while its iterative sampling process is computationallyexpensive. In this work, we propose a diffusion model combined with aGenerative Adversarial Network, aiming to (i) alleviate one of the remainingchallenges in algorithmic music generation which is the control of generationtowards a target emotion, and (ii) mitigate the slow sampling drawback ofdiffusion models applied to symbolic music generation. We first used a trainedVariational Autoencoder to obtain embeddings of a symbolic music dataset withemotion labels and then used those to train a diffusion model. Our resultsdemonstrate the successful control of our diffusion model to generate symbolicmusic with a desired emotion. Our model achieves several orders of magnitudeimprovement in computational cost, requiring merely four time steps to denoisewhile the steps required by current state-of-the-art diffusion models forsymbolic music generation is in the order of thousands.

Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotions