Papers
arxiv:2308.04729

JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models

Published on Aug 9, 2023
· Submitted by akhaliq on Aug 10, 2023
#1 Paper of the day
Authors:
,
,
,

Abstract

Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical structures and high sampling rate requirements. Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization. This paper introduces JEN-1, a universal high-fidelity model for text-to-music generation. JEN-1 is a diffusion model incorporating both autoregressive and non-autoregressive training. Through in-context learning, JEN-1 performs various generation tasks including text-guided music generation, music inpainting, and continuation. Evaluations demonstrate JEN-1's superior performance over state-of-the-art methods in text-music alignment and music quality while maintaining computational efficiency. Our demos are available at http://futureverse.com/research/jen/demos/jen1

Community

The demos link is not working, please check

It is working now. :)

Great job guys!

So what's the plan for this? Is there a product coming? I can already think about a number of interesting things I could use this very interesting model for. :-)

They want to make a Huggingface Space and Google Colab of JEN-1 Demo!

Paper author

https://www.jenmusic.ai/, app is coming soon!

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2308.04729 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2308.04729 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2308.04729 in a Space README.md to link it from this page.

Collections including this paper 1