mlsanityData to 7 Oct 2026

Cold Diffusion for Speech Enhancement

arXiv 2211.02527 ↗First posted 4 Nov 2022eess.AS cs.SDcited by 31

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

Abstract (arXiv)

Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a recently proposed advanced iterative diffusion model, namely cold diffusion, to recover clean speech signals from noisy signals. The unique mathematical properties of the sampling process from cold diffusion could be utilized to restore high-quality samples from arbitrary degradations. Based on these properties, we propose an improved training algorithm and objective to help the model generalize better during the sampling process. We verify our proposed framework by investigating two model architectures. Experimental results on benchmark speech enhancement dataset VoiceBank-DEMAND demonstrate the strong performance of the proposed approach compared to representative discriminative models and diffusion-based enhancement models.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 25 of its 42 references that are in the map. First posted on arXiv 4 Nov 2022.

Builds on

25 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain31 Mar
  2. 2022Conditional Diffusion Probabilistic Model for Speech Enhancement10 Feb
  3. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Model25 Jul
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  8. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 275
  9. 2017Deep Complex Networkscited by 215
  10. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  11. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  12. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
9 more
  1. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  2. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  3. 2021Variational Autoencoder for Speech Enhancement with a Noise-Aware Encodercited by 28
  4. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  5. 2018Speech Denoising with Deep Feature Lossescited by 26
  6. 2021A Flow-Based Neural Network for Time Domain Speech Enhancementcited by 16
  7. 2020WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancementcited by 12
  8. 2021S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancementcited by 12
  9. 2021Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancementcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 5; 2025: 7; 2026: 4.

31 papers.

Sort:

By area:

  1. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  2. 2023CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalizationcited by 51
  3. 2023Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approachcited by 21
  4. 2023The Ethical Implications of Generative Audio Models: A Systematic Literature Reviewcited by 18
  5. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  6. 2023Single and Few-step Diffusion for Generative Speech Enhancementcited by 15
  7. 2023Unsupervised speech enhancement with diffusion-based generative modelscited by 12
  8. 2023Investigating the Design Space of Diffusion Models for Speech Enhancementcited by 10
  9. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  10. 2023DDTSE: Discriminative Diffusion Model for Target Speech Extractioncited by 8
  11. 2023Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Samplercited by 8
  12. 2023Reconstruction of Sound Field through Diffusion Modelscited by 8
19 more
  1. 2024Diffusion-based Unsupervised Audio-visual Speech Enhancementcited by 8
  2. 2024Structured Diffusion Models with Mixture of Gaussians as Prior Distributioncited by 8
  3. 2023Diffusion-based speech enhancement with a weighted generative-supervised learning losscited by 7
  4. 2023Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancementcited by 5
  5. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
  6. 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extractioncited by 4
  7. 2024The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systemscited by 3
  8. 2025A Survey of Deep Learning for Complex Speech Spectrogramscited by 3
  9. 2025Adaptive Deterministic Flow Matching for Target Speaker Extractioncited by 2
  10. 2024AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologiescited by 1
  11. 2025Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancementcited by 1
  12. 2025Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancementcited by 1
  13. 2023Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencodercited by 0
  14. 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Priorcited by 0
  15. 2025Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancementcited by 0
  16. 2026A Cold Diffusion Approach for Percussive Dereverberationcited by 0
  17. 2026GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalizationcited by 0
  18. 2026Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstructioncited by 0
  19. 2026Transformer-based Neural Beamforming for Real-Time Speech Enhancement on Smart Low-Power Hearable Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models
  2. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
  3. 2024Diffusion Models for Audio Restoration
  4. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration
  5. 2025Combining Deterministic Enhanced Conditions with Dual-Streaming Encoding for Diffusion-Based Speech Enhancement
  6. 2023NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement
  7. 2026Absorbing Discrete Diffusion for Speech Enhancement
  8. 2024GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient Speech Enhancement