Steer Unified Audio Editing Toward Reliable Source Selection
cs.SD
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/GeWu-Lab/SteerSound
Project page: https://gewu-lab.github.io/SteerSound
Terminology
Sources
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
- Classifier-Free Diffusion Guidance
- Efficient Training of Audio Transformers with Patchout
- A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
- UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion
- Flow Matching for Generative Modeling
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
- Transfer between Modalities with MetaQueries
- SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
- SAM Audio: Segment Anything in Audio
- SeedEdit: Align Image Re-Generation to Image Editing
- MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
- Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
- Prompt-guided Precise Audio Editing with Diffusion Models
- MOSS-Audio Technical Report
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems