English

Improving Musical Accompaniment Co-creation via Diffusion Transformers

Sound 2024-10-31 v1 Audio and Speech Processing

Abstract

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the underlying autoencoder to a stereo-capable model with superior fidelity and replace the latent U-Net with a Diffusion Transformer. Additionally, we refine text prompting by training a cross-modality predictive network to translate text-derived CLAP embeddings to audio-derived CLAP embeddings. Finally, we improve inference speed by training the latent model using a consistency framework, achieving competitive quality with fewer denoising steps. Our model is evaluated against the original Diff-A-Riff variant using objective metrics in ablation experiments, demonstrating promising advancements in all targeted areas. Sound examples are available at: https://sonycslparis.github.io/improved_dar/.

Keywords

Cite

@article{arxiv.2410.23005,
  title  = {Improving Musical Accompaniment Co-creation via Diffusion Transformers},
  author = {Javier Nistal and Marco Pasini and Stefan Lattner},
  journal= {arXiv preprint arXiv:2410.23005},
  year   = {2024}
}

Comments

5 pages; 1 table

R2 v1 2026-06-28T19:41:11.517Z