mlsanityData to 7 Oct 2026

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

arXiv 2104.03538 ↗First posted 8 Apr 2021cs.SD cs.AI eess.AScited by 114

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three training techniques incorporating domain-knowledge of speech processing are proposed. With these techniques, experimental results on the VoiceBank-DEMAND dataset show that MetricGAN+ can increase PESQ score by 0.3 compared to the previous MetricGAN and achieve state-of-the-art results (PESQ score = 3.15).

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

26 of 44 references.

References · 26

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  3. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  4. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
  5. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  6. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  8. 2017HashNet: Deep Learning to Hash by Continuationcited by 121
  9. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  10. 2019PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Networkcited by 49
  11. 2020HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networkscited by 40
  12. 2018Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTMcited by 36
14 more
  1. 2020Speech Enhancement using Self-Adaptation and Multi-Head Self-Attentioncited by 28
  2. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
  3. 2020A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differencescited by 22
  4. 2020Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Modelscited by 10
  5. 2018Spectral feature mapping with mimic loss for robust speech recognitioncited by 8
  6. 2018DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Scorecited by 8
  7. 2019End-to-End Multi-Task Denoising for joint SDR and PESQ Optimizationcited by 8
  8. 2019Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Qualitycited by 8
  9. 2020SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learningcited by 6
  10. 2020iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learningcited by 4
  11. 2018Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measurecited by 3
  12. 2020Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processingcited by 3
  13. 2018Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASRcited by 2
  14. 2020Stable Training of DNN for Speech Enhancement based on Perceptually-Motivated Black-Box Cost Functioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 21; 2023: 22; 2024: 22; 2025: 26; 2026: 13.

114 papers.

Sort:

By area:

  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  2. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  3. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  4. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  5. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  6. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
  7. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  8. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
  9. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  10. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  11. 2021Learning Audio-Visual Dereverberationcited by 26
  12. 2023Spiking Structured State Space Model for Monaural Speech Enhancementcited by 23
38 more
  1. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  2. 2023AV-RIR: Audio-Visual Room Impulse Response Estimationcited by 20
  3. 2021MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speechcited by 18
  4. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementcited by 18
  5. 2021Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transportcited by 16
  6. 2023AdVerb: Visually Guided Audio Dereverberationcited by 15
  7. 2023Self-Supervised Visual Acoustic Matchingcited by 14
  8. 2022Speech Denoising in the Waveform Domain with Self-Attentioncited by 13
  9. 2024The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancementcited by 12
  10. 2021Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problemcited by 11
  11. 2023Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoderscited by 10
  12. 2024Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancementcited by 10
  13. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  14. 2023Noise-aware Speech Enhancement using Diffusion Probabilistic Modelcited by 9
  15. 2024BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embeddingcited by 9
  16. 2024Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolutioncited by 9
  17. 2022Music Separation Enhancement with Generative Modelingcited by 8
  18. 2022SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Taskscited by 8
  19. 2023Perceive and predict: self-supervised speech representation based loss functions for speech enhancementcited by 8
  20. 2024Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise Schedulecited by 8
  21. 2021REAL-M: Towards Speech Separation on Real Mixturescited by 7
  22. 2022FFC-SE: Fast Fourier Convolution for Speech Enhancementcited by 7
  23. 2023SE-Bridge: Speech Enhancement with Consistent Brownian Bridgecited by 7
  24. 2024FINALLY: fast and universal speech enhancement with studio-like qualitycited by 7
  25. 2022Perceptual Contrast Stretching on Target Feature for Speech Enhancementcited by 6
  26. 2022Multi-View Attention Transfer for Efficient Speech Enhancementcited by 6
  27. 2024Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridgecited by 6
  28. 2024TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancementcited by 6
  29. 2022MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Datacited by 5
  30. 2022A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancementcited by 5
  31. 2022Improving Speech Enhancement through Fine-Grained Speech Characteristicscited by 5
  32. 2023Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancementcited by 5
  33. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
  34. 2024Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translationcited by 5
  35. 2022Exploring Self-Attention Mechanisms for Speech Separationcited by 4
  36. 2024MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancementcited by 4
  37. 2025xLSTM-SENet: xLSTM for Single-Channel Speech Enhancementcited by 4
  38. 2025Robust One-step Speech Enhancement via Consistency Distillationcited by 4

50 most cited of 114 All 114 (JSON)