SDLGASApr 16, 2024

Long-form music generation with latent diffusion

arXiv:2404.10301v2110 citationsh-index: 9ISMIR
Originality Highly original
AI Analysis

This addresses the challenge for musicians and content creators who need AI-generated music with long-term coherence, representing a significant advance over prior methods.

The paper tackled the problem of generating full-length music tracks with coherent structure from text prompts, achieving state-of-the-art results with music up to 4 minutes and 45 seconds long.

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 4m45s. 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes