mlsanityData to 7 Oct 2026

CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement

arXiv 2209.11112 ↗First posted 22 Sep 2022cs.SD cs.AI cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

In this work, we further develop the conformer-based metric generative adversarial network (CMGAN) model for speech enhancement (SE) in the time-frequency (TF) domain. This paper builds on our previous work but takes a more in-depth look by conducting extensive ablation studies on model inputs and architectural design choices. We rigorously tested the generalization ability of the model to unseen noise types and distortions. We have fortified our claims through DNS-MOS measurements and listening tests. Rather than focusing exclusively on the speech denoising task, we extend this work to address the dereverberation and super-resolution tasks. This necessitated exploring various architectural changes, specifically metric discriminator scores and masking techniques. It is essential to highlight that this is among the earliest works that attempted complex TF-domain super-resolution. Our findings show that CMGAN outperforms existing state-of-the-art methods in the three major speech enhancement tasks: denoising, dereverberation, and super-resolution. For example, in the denoising task using the Voice Bank+DEMAND dataset, CMGAN notably exceeded the performance of prior models, attaining a PESQ score of 3.41 and an SSNR of 11.10 dB. Audio samples and CMGAN implementations are available online.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 59 of its 133 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

59 of 133 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  7. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  11. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  12. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
38 more
  1. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  2. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  3. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  4. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 165
  5. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
  6. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  7. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  8. 2019Deep Learning for Audio Signal Processingcited by 92
  9. 2020An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separationcited by 81
  10. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  11. 2020Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separationcited by 67
  12. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 57
  13. 2019PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Networkcited by 49
  14. 2017A Wavenet for Speech Denoisingcited by 47
  15. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  16. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  17. 2018Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTMcited by 36
  18. 2019Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulationscited by 36
  19. 2020Continuous Speech Separation with Conformercited by 36
  20. 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 36
  21. 2021DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancementcited by 33
  22. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
  23. 2021Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancementcited by 25
  24. 2018Improved Speech Enhancement with the Wave-U-Netcited by 23
  25. 2020Improving GANs for Speech Enhancementcited by 22
  26. 2017Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verificationcited by 19
  27. 2017Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognitioncited by 19
  28. 2020A consolidated view of loss functions for supervised deep learning-based speech enhancementcited by 19
  29. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementcited by 18
  30. 2021DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancementcited by 16
  31. 2018Speech Dereverberation Using Fully Convolutional Networkscited by 14
  32. 2018Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspectivecited by 13
  33. 2020SESQA: semi-supervised learning for speech quality assessmentcited by 13
  34. 2020SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mappingcited by 12
  35. 2020Interactive Speech and Noise Modeling for Speech Enhancementcited by 12
  36. 2021On The Compensation Between Magnitude and Phase in Speech Separationcited by 12
  37. 2019Non-intrusive speech quality assessment using neural networkscited by 11
  38. 2021A Simultaneous Denoising and Dereverberation Framework with Target Decouplingcited by 11

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 13; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023AUDIT: Audio Editing by Following Instructions with Latent Diffusion Modelscited by 81
  2. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  3. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
  4. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 38
  5. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  6. 2025xLSTM-SENet: xLSTM for Single-Channel Speech Enhancementcited by 4
  7. 2025A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancementcited by 4
  8. 2025Schr"odinger Bridge Consistency Trajectory Models for Speech Enhancementcited by 4
  9. 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancementcited by 4
  10. 2025Linguistic Knowledge Transfer Learning for Speech Enhancementcited by 3
  11. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  12. 2023Exploiting Time-Frequency Conformers for Music Audio Enhancementcited by 2
10 more
  1. 2025CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASRcited by 2
  2. 2025MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancementcited by 2
  3. 2024Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancementcited by 1
  4. 2025Investigating training objective for flow matching-based speech enhancementcited by 1
  5. 2024TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognitioncited by 0
  6. 2025VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identificationcited by 0
  7. 2025Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch Boostingcited by 0
  8. 2025A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environmentscited by 0
  9. 2026Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergycited by 0
  10. 2026RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillationcited by 0