AI Paper Atlas

Research map / Video / Video generation

AV-Edit: Multimodal Generative Sound Effect Editing via Audio-Visual Semantic Joint Control

Xinyue Guo, Xiaoran Yang, Lipan Zhang, Jianxuan Yang, Zhao Wang, Jian Luan

AAAI 2026 · Video › Video generation · approach: Video-to-audio synthesis · 1 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
add spectrogram segmenting (ablation)CAV-MAE-Edit · VGGSoundaudio MAE loss: 2.219 -> 0.450Improved
add spectrogram segmenting (ablation)CAV-MAE-Edit · VGGSoundtotal loss: 3.569 -> 1.632Improved
add global tokens (ablation)CAV-MAE-Edit · VGGSoundcontrastive loss: 8.552 -> 0.807Improved
add audio mixing (ablation)CAV-MAE-Edit · VGGSoundaudio MAE loss: 0.400 -> 0.661Hurt
add audio mixing (ablation)CAV-MAE-Edit · VGGSoundtotal loss: 1.350 -> 1.297Improved
add text prompt input (ablation)AV-Edit · VGG-Edit RemovalFD: 27.56 -> 25.24Improved
add text prompt input (ablation)AV-Edit · VGG-Edit ReplacementFD: 48.24 -> 38.00Improved
add text prompt input (ablation)AV-Edit · VGG-Edit (subjective)instruction adherence: 68.0 -> 70.8Improved
add text prompt input (ablation)AV-Edit · VGG-Edit (subjective)fidelity: 64.4 -> 62.4Hurt
feed original audio features into generation (ablation)AV-Edit · VGGSound testInception Score: 23.08 -> 22.48Hurt
use AV-Edit instead of AudioX/DeepSound for editingAV-Edit · VGG-Edit ReplacementFD: 79.64 -> 38.00 (vs AudioX)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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