mlsanityData to 7 Oct 2026

Conditional Diffusion Probabilistic Model for Speech Enhancement

arXiv 2202.05256 ↗First posted 10 Feb 2022eess.AS cs.LG cs.SDcited by 132

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

Abstract (arXiv)

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are still lagging behind in speech enhancement. This work leverages recent advances in diffusion probabilistic models, and proposes a novel speech enhancement algorithm that incorporates characteristics of the observed noisy speech signal into the diffusion and reverse processes. More specifically, we propose a generalized formulation of the diffusion probabilistic model named conditional diffusion probabilistic model that, in its reverse process, can adapt to non-Gaussian real noises in the estimated speech signal. In our experiments, we demonstrate strong performance of the proposed approach compared to representative generative models, and investigate the generalization capability of our models to other datasets with noise characteristics unseen during training.

Key facts. Cited by 132 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 22 of its 36 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

22 of 36 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Model25 Jul
  2. 2021DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion28 May
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  6. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  7. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  8. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  9. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  10. 2019A Recurrent Variational Autoencoder for Speech Enhancementcited by 38
  11. 2020Far-Field Automatic Speech Recognitioncited by 32
  12. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
7 more
  1. 2020Improving GANs for Speech Enhancementcited by 22
  2. 2019Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modelingcited by 21
  3. 2017Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verificationcited by 19
  4. 2021A Flow-Based Neural Network for Time Domain Speech Enhancementcited by 16
  5. 2020WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancementcited by 12
  6. 2018Spectral feature mapping with mimic loss for robust speech recognitioncited by 8
  7. 2018DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Scorecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 18; 2023: 35; 2024: 25; 2025: 38; 2026: 16.

132 papers.

Sort:

By area:

  1. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  2. 2023Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Modelcited by 145
  3. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  4. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domaincited by 102
  5. 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency modelscited by 99
  6. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  7. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  8. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  9. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 62
  10. 2022Conditional Simulation Using Diffusion Schr"odinger Bridgescited by 58
  11. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  12. 2022BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesiscited by 44
38 more
  1. 2022Diffusion-based Generative Speech Source Separationcited by 41
  2. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  3. 2024Diffusion Models for Audio Restorationcited by 32
  4. 2022Cold Diffusion for Speech Enhancementcited by 31
  5. 2023Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancementcited by 30
  6. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  7. 2023The Ethical Implications of Generative Audio Models: A Systematic Literature Reviewcited by 18
  8. 2025FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matchingcited by 17
  9. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  10. 2023Target Speech Extraction with Conditional Diffusion Modelcited by 15
  11. 2023Single and Few-step Diffusion for Generative Speech Enhancementcited by 15
  12. 2025Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representationcited by 15
  13. 2022Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancementcited by 14
  14. 2022SRTNet: Time Domain Speech Enhancement Via Stochastic Refinementcited by 12
  15. 2023Unsupervised speech enhancement with diffusion-based generative modelscited by 12
  16. 2023DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extractioncited by 12
  17. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  18. 2023Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaptioncited by 11
  19. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocodercited by 10
  20. 2023Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASRcited by 10
  21. 2023Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoderscited by 10
  22. 2023Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communicationscited by 10
  23. 2023Investigating the Design Space of Diffusion Models for Speech Enhancementcited by 10
  24. 2023Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Modelscited by 9
  25. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  26. 2023Diffusion Posterior Sampling for Informed Single-Channel Dereverberationcited by 9
  27. 2023Noise-aware Speech Enhancement using Diffusion Probabilistic Modelcited by 9
  28. 2024Noise-robust Speech Separation with Fast Generative Correctioncited by 9
  29. 2024BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embeddingcited by 9
  30. 2022ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understandingcited by 8
  31. 2022NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTScited by 8
  32. 2022DiffPhase: Generative Diffusion-based STFT Phase Retrievalcited by 8
  33. 2023Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Samplercited by 8
  34. 2024Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancementcited by 8
  35. 2024Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise Schedulecited by 8
  36. 2024Diffusion-based Unsupervised Audio-visual Speech Enhancementcited by 8
  37. 2023SE-Bridge: Speech Enhancement with Consistent Brownian Bridgecited by 7
  38. 2023Diffusion-based speech enhancement with a weighted generative-supervised learning losscited by 7

50 most cited of 132 All 132 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement
  2. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
  3. 2025GDiffuSE: Diffusion-based speech enhancement with noise model guidance
  4. 2023Diffusion-based Signal Refiner for Speech Enhancement and Separation
  5. 2023Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data
  6. 2026Rethinking Flow and Diffusion Bridge Models for Speech Enhancement
  7. 2025FlowSE: Flow Matching-based Speech Enhancement
  8. 2025Speech Enhancement based on cascaded two flows