TensorX
返回文献探索

Paper · arXiv 2311.00613

Controllable Music Production with Diffusion Models and Guidance Gradients

Mark Levy, Bruno Di Giorgi, Floris Weers, Angelos Katharopoulos, Tom Nickson

24 upvotesNovember 1, 2023arXiv 预印本
AI 摘要

Conditional generation from diffusion models is used for various music production tasks using sampling-time guidance, ensuring context matching and conforming to class distributions.

diffusion modelsconditional generationmusical audiosampling-time guidancecontinuationinpaintingregenerationsmooth transitionsstylistic characteristicsreconstruction lossesclassification lossespre-trained classifierlatent representationembedding model

Abstract

We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44.1kHz stereo audio with sampling-time guidance. The scenarios we consider include continuation, inpainting and regeneration of musical audio, the creation of smooth transitions between two different music tracks, and the transfer of desired stylistic characteristics to existing audio clips. We achieve this by applying guidance at sampling time in a simple framework that supports both reconstruction and classification losses, or any combination of the two. This approach ensures that generated audio can match its surrounding context, or conform to a class distribution or latent representation specified relative to any suitable pre-trained classifier or embedding model.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
Controllable Music Production with Diffusion Models and Guidance Gradients | TensorX