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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add spectrogram segmenting (ablation) | CAV-MAE-Edit · VGGSound | audio MAE loss: 2.219 -> 0.450 | Improved |
| add spectrogram segmenting (ablation) | CAV-MAE-Edit · VGGSound | total loss: 3.569 -> 1.632 | Improved |
| add global tokens (ablation) | CAV-MAE-Edit · VGGSound | contrastive loss: 8.552 -> 0.807 | Improved |
| add audio mixing (ablation) | CAV-MAE-Edit · VGGSound | audio MAE loss: 0.400 -> 0.661 | Hurt |
| add audio mixing (ablation) | CAV-MAE-Edit · VGGSound | total loss: 1.350 -> 1.297 | Improved |
| add text prompt input (ablation) | AV-Edit · VGG-Edit Removal | FD: 27.56 -> 25.24 | Improved |
| add text prompt input (ablation) | AV-Edit · VGG-Edit Replacement | FD: 48.24 -> 38.00 | Improved |
| add text prompt input (ablation) | AV-Edit · VGG-Edit (subjective) | instruction adherence: 68.0 -> 70.8 | Improved |
| add text prompt input (ablation) | AV-Edit · VGG-Edit (subjective) | fidelity: 64.4 -> 62.4 | Hurt |
| feed original audio features into generation (ablation) | AV-Edit · VGGSound test | Inception Score: 23.08 -> 22.48 | Hurt |
| use AV-Edit instead of AudioX/DeepSound for editing | AV-Edit · VGG-Edit Replacement | FD: 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.
- AudioX — AudioX: A Unified Framework for Anything-to-Audio Generation (ICLR 2026) · better on 4 of 4 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
- AVENUE: Audio-Video Editing Understanding and Evaluation (NeurIPS 2026 · similarity 0.89)
- SoundBrush: Sound as a Brush for Visual Scene Editing (AAAI 2025 · similarity 0.88)
- Read, Watch and Scream! Sound Generation from Text and Video (AAAI 2025 · similarity 0.88)
- Prompt-guided Precise Audio Editing with Diffusion Models (ICML 2024 · similarity 0.87)
- SAO-Instruct: Free-form Audio Editing using Natural Language Instructions (NeurIPS 2025 · similarity 0.87)
- AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation (ICML 2026 · similarity 0.87)
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.
