mlsanityData to 14 Oct 2026

Virtual Consistency for Audio Editing

arXiv 2509.17219 ↗First posted 21 Sep 2025cs.SD cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

25 of 30 references.

References · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  5. 2023Consistency Modelscited by 1,822
  6. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  7. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  8. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  9. 2023Simple and Controllable Music Generationcited by 488
  10. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 344
  11. 2022AudioGen: Textually Guided Audio Generationcited by 295
  12. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 137
13 more
  1. 2023Inversion-Free Image Editing with Natural Languagecited by 106
  2. 2023AUDIT: Audio Editing by Following Instructions with Latent Diffusion Modelscited by 83
  3. 2025MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantizationcited by 68
  4. 2024Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversioncited by 60
  5. 2024DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generationcited by 26
  6. 2023InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Modelscited by 23
  7. 2024Prompt-guided Precise Audio Editing with Diffusion Modelscited by 18
  8. 2024High Fidelity Text-Guided Music Editing via Single-Stage Flow Matchingcited by 13
  9. 2024Editing Music with Melody and Text: Using ControlNet for Diffusion Transformercited by 13
  10. 2024Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuningcited by 12
  11. 2023Audio Editing with Non-Rigid Text Promptscited by 8
  12. 2024MEDIC: Zero-shot Music Editing with Disentangled Inversion Controlcited by 8
  13. 2025SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editingcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
  2. 2024AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework
  3. 2025AudioMorphix: Training-free audio editing with diffusion probabilistic models
  4. 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
  5. 2025Guiding Audio Editing with Audio Language Model
  6. 2025Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis
  7. 2026Stable Audio 3
  8. 2026RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers