mlsanityData to 19 Oct 2026

Speech enhancement and noise suppression

892 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: enhancement, speech enhancement, speech, noise, performance

Key facts. Speech enhancement and noise suppression: 892 papers on arXiv since 2021 (data through 19 Oct 2026). 148 of its 892 mapped papers (17%) cite “Speech Enhancement and Dereverberation with Diffusion-based Generative Models” (2022, arXiv 2208.05830). 6 new papers 2 Oct–19 Oct.

What’s new

2 Oct – 19 Oct 2026

6 new papers, 2 Oct – 19 Oct; 0 this week.

  1. Earlier · 6
  2. Rethinking Batch Composition: Promoting Feature Diversity for Speech Enhancement
  3. CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge
  4. Spiking Neural Beamforming for Multichannel Speech Enhancement on the Edge
  5. Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search
  6. LIFT-SE: Linguistic Inference Followed by Flow Transformation for Generative Speech Enhancement also fits: Vocoders and speech synthesis
  7. UltraM2M: Leveraging Text Transcripts and Mixture Constraints for Weakly-Supervised Speech Enhancement

Foundations

Most cited by papers here

  1. Speech Enhancement and Dereverberation with Diffusion-based Generative Models2022cited by 148 here
  2. MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement2021cited by 123 here
  3. Conditional Diffusion Probabilistic Model for Speech Enhancement2022cited by 117 here
  4. StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation2022cited by 102 here
  5. Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain2022cited by 75 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Modelcited by 37 here
  2. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 117 here
  3. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domaincited by 75 here
  4. 2022Universal Speech Enhancement with Score-based Diffusioncited by 55 here
  5. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 148 here
  6. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 102 here
18 more it builds on, not in this chain
  1. 2021Towards efficient models for real-time deep noise suppressioncited by 42 here
  2. 2021Variational Autoencoder for Speech Enhancement with a Noise-Aware Encodercited by 36 here
  3. 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 45 here
  4. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 123 here
  5. 2021DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancementcited by 35 here
  6. 2021Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancementcited by 44 here
  7. 2021DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filteringcited by 43 here
  8. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 91 here
  9. 2022How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASRcited by 42 here
  10. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 57 here
  11. 2022DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audiocited by 40 here
  12. 2022FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancementcited by 39 here
  13. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 44 here
  14. 2022TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separationcited by 60 here
  15. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 87 here
  16. 2023MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectracited by 62 here
  17. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 55 here
  18. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 36 here

The 24 most cited of 996.

Browse

30 of 892, ranked 6–35

  1. 6MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra202362
  2. 7CMGAN: Conformer-based Metric GAN for Speech Enhancement202257
  3. 8An Investigation of Incorporating Mamba for Speech Enhancement202455
  4. 9Universal Speech Enhancement with Score-based Diffusion202255
  5. 10TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain202145
  6. 11CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement202244
  7. 12Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement202144
  8. 13DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering202143
  9. 14How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR202242
  10. 15Towards efficient models for real-time deep noise suppression202142
All 30
  1. 16DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio202240
  2. 17FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement202239
  3. 18A Study on Speech Enhancement Based on Diffusion Probabilistic Model202137
  4. 19EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation202436
  5. 20Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder202136
  6. 21SELM: Speech Enhancement Using Discrete Tokens and Language Models202335
  7. 22DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement202135
  8. 23Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders202133
  9. 24DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement202132
  10. 25On The Compensation Between Magnitude and Phase in Speech Separation202132
  11. 26Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement202131
  12. 27Schr"odinger Bridge for Generative Speech Enhancement202430
  13. 28Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement202329
  14. 29FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement202229
  15. 30RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing202228
  16. 31Real-time Denoising and Dereverberation with Tiny Recurrent U-Net202128
  17. 32URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement202427
  18. 33Universal Score-based Speech Enhancement with High Content Preservation202427
  19. 34HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement202227
  20. 35Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration202226