mlsanityData to 7 Oct 2026

Unsupervised vocal dereverberation with diffusion-based generative models

arXiv 2211.04124 ↗First posted 8 Nov 2022eess.AS cs.LG cs.SDcited by 18

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Removing reverb from reverberant music is a necessary technique to clean up audio for downstream music manipulations. Reverberation of music contains two categories, natural reverb, and artificial reverb. Artificial reverb has a wider diversity than natural reverb due to its various parameter setups and reverberation types. However, recent supervised dereverberation methods may fail because they rely on sufficiently diverse and numerous pairs of reverberant observations and retrieved data for training in order to be generalizable to unseen observations during inference. To resolve these problems, we propose an unsupervised method that can remove a general kind of artificial reverb for music without requiring pairs of data for training. The proposed method is based on diffusion models, where it initializes the unknown reverberation operator with a conventional signal processing technique and simultaneously refines the estimate with the help of diffusion models. We show through objective and perceptual evaluations that our method outperforms the current leading vocal dereverberation benchmarks.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 18 of its 39 references that are in the map. First posted on arXiv 8 Nov 2022.

Builds on

18 of 39 references.

References · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2017Mixed Precision Trainingcited by 1,135
  7. 2017Deep Image Priorcited by 1,097
  8. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  9. 2022Denoising Diffusion Restoration Modelscited by 951
  10. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  11. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  12. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
6 more
  1. 2018Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithmscited by 221
  2. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  3. 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
  4. 2020NHSS: A Speech and Singing Parallel Databasecited by 16
  5. 2022Music Enhancement via Image Translation and Vocodingcited by 11
  6. 2021Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Networkcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 4; 2025: 4; 2026: 2.

18 papers.

Sort:

By area:

  1. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  2. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  3. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 128
  4. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  5. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  6. 2023Multi-Source Diffusion Models for Simultaneous Music Generation and Separationcited by 63
  7. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 58
  8. 2024Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Modelscited by 11
  9. 2023On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularizationcited by 10
  10. 2024BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Modelscited by 9
  11. 2023Zero-Shot Duet Singing Voices Separation with Diffusion Modelscited by 6
  12. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
6 more
  1. 2025A Hybrid Model for Weakly-Supervised Speech Dereverberationcited by 2
  2. 2025Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Samplingcited by 2
  3. 2026Outlier-Robust Diffusion Solvers for Inverse Problemscited by 1
  4. 2025Unsupervised Multi-channel Speech Dereverberation via Diffusioncited by 0
  5. 2025Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challengescited by 0
  6. 2026A Cold Diffusion Approach for Percussive Dereverberationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation
  2. 2026Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation
  3. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models
  4. 2023Diffusion Posterior Sampling for Informed Single-Channel Dereverberation
  5. 2025Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model
  6. 2025Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures
  7. 2024Diffusion Models for Audio Restoration
  8. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Model