analiza aiqbench
This arXiv paper is primarily about AI: a diffusion-GAN hybrid for generating symbolic music, with emotion control and a claimed reduction to about 15 denoising steps. The core contribution is a faster sampling approach for diffusion models on discrete music data, using pianoroll representations and a VAE latent space. For AI readers, the key question is whether the speed and emotion-control claims hold up against established symbolic music baselines, which the abstract alone does not establish.
Fast Diffusion-GAN Model for Generating Symbolic Music with Emotions
arXiv:2310.14040v2 Announce Type: replace-cross Abstract: Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate symbolic music since this class of generative models struggles with discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model integrated with a Generative Adversarial Network, aiming to mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We enable the use of diffusion model by representing symbolic music as image-like pianorolls with velocity values instead of discrete event tokens and then used a Variational Autoencoder to obtain their latent representations to train the proposed diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model uses merely 15 denoising diffusion steps to produce high-quality music, while most diffusion models for symbolic music generation require hundreds or thousands of steps.
Abstract:Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate symbolic music since this class of generative models struggles with discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model integrated with a Generative Adversarial Network, aiming to mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We enable the use of diffusion model by representing symbolic music as image-like pianorolls with velocity values instead of discrete event tokens and then used a Variational Autoencoder to obtain their latent representations to train the proposed diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model uses merely 15 denoising diffusion steps to produce high-quality music, while most diffusion models for symbolic music generation require hundreds or thousands of steps.
Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
arXiv:2310.14040 [cs.SD]
(or arXiv:2310.14040v2 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2310.14040 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 265 cuvinte
Subiecte conexe
Game Design Creativity evals
LessWrong · 12 oct. 2026
Getting Started with OmniVoice-Studio
KDnuggets · 23 iul. 2026
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
arXiv · 30 sept. 2026
Self-Representation Alignment in Diffusion Models for Video Background Music Generation
arXiv · 15 oct. 2026