Work

Long-Form Music Generation With Latent Diffusion

Year: 2024

Type: conference-paper

Abstract: Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long temporal contexts it is possible to produce long-form music of up to 4m 45s. Our model consists of a diffusion-transformer operating on a highly downsampled continuous latent representation (latent rate of 21.5Hz). It obtains state-of-the-art generations according to metrics on audio quality and prompt alignment, and subjective tests reveal that it produces full-length music with coherent structure.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.14877070

Authors: Zach Evans, Julian D. Parker, CJ Carr, Zachary Zukowski, Josiah Taylor, Jordi Pons

Language: English

Topic: Music and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W6968638440

FWCI:

Cites:

Cited by:

Related to: