AV-Edit: Multimodal Generative Sound Effect Editing via Audio-Visual Semantic Joint Control
Preprint
Abstract
Sound effect editing-modifying audio by adding, removing, or replacing elements-remains constrained by existing approaches that rely solely on low-level signal processing or coarse text prompts, often resulting in limited flexibility and suboptimal audio quality. To address this, we propose AV-Edit, a generative sound effect editing framework that enables fine-grained editing of existing audio tracks in videos by jointly leveraging visual, audio, and text semantics. Specifically, the proposed method employs a specially designed contrastive audio-visual masking autoencoder (CAV-MAE-Edit) for multimodal pre-training, learning aligned cross-modal representations. These representations are then used to train an editorial Multimodal Diffusion Transformer (MM-DiT) capable of removing visually irrelevant sounds and generating missing audio elements consistent with video content through a correlation-based feature gating training strategy. Furthermore, we construct a dedicated video-based sound editing dataset as an evaluation benchmark. Experiments demonstrate that the proposed AV-Edit generates high-quality audio with precise modifications based on visual content, achieving state-of-the-art performance in the field of sound effect editing and exhibiting strong competitiveness in the domain of audio generation.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized SoundsInternational Journal of Computer Vision, 2026
- WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal ResearchIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
- Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching2024
- AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models2023
- UAVM: Towards Unifying Audio and Visual ModelsIEEE Signal Processing Letters, 2022
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Sur quelques points du calcul fonctionnelRendiconti del Circolo Matematico di Palermo Series 2, 1906