AI Paper Atlas

Research map / Image generation / Editing and style transfer

AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models

Yuancheng Wang, Zeqian Ju, Xu Tan, Lei He, Zhizheng Wu, Jiang Bian, sheng zhao

NeurIPS 2023 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove caption text input at inference (ablation)AUDIT · InpaintingFD: 18.17 -> 19.03Mixed
remove caption text input at inference (ablation)AUDIT · Super-resolutionFD: 18.14 -> 21.97Hurt
remove caption text input (ablation)SDEdit-Precise baseline · InpaintingFD: 21.07 -> 27.63Hurt
remove caption text input (ablation)SDEdit-Precise baseline · Super-resolutionFD: 27.81 -> 32.66Hurt
use precise masked region instead of rough region (ablation)SDEdit · InpaintingFD: 21.99 -> 21.07Improved
replace SDEdit with instruction-trained AUDITSDEdit-1/4T · AddingFD: 28.25 -> 21.80Improved
replace SDEdit with AUDITSDEdit-1/2T · DroppingFD: 28.19 -> 22.40Improved
replace SDEdit with AUDITSDEdit-1/4T · ReplacementFD: 26.72 -> 21.65Improved
reduce SDEdit denoising steps from 3/4T to 1/4TSDEdit · AddingFD: 28.87 -> 28.25Improved
reduce SDEdit denoising steps from 3/4T to 1/4TSDEdit · DroppingFD: 29.66 -> 31.31No clear effect
use AUDIT text-to-audio model vs AudioLDM-L-Fulltext-to-audio model · AudioCapsFD: 23.31 -> 20.19Improved
use AUDIT instead of best baseline (subjective)AUDIT · DroppingRelevance: 48.2 -> 81.0Improved

Later papers that compared with this method

1 later accepted paper reports Audit as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy