mlsanityData to 7 Oct 2026

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

arXiv 1905.04874 ↗First posted 13 May 2019cs.SD cs.LG eess.AScited by 104

Not on the map. Why?

Abstract (arXiv)

Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric scores. To overcome this issue, we propose a novel MetricGAN approach with an aim to optimize the generator with respect to one or multiple evaluation metrics. Moreover, based on MetricGAN, the metric scores of the generated data can also be arbitrarily specified by users. We tested the proposed MetricGAN on a speech enhancement task, which is particularly suitable to verify the proposed approach because there are multiple metrics measuring different aspects of speech signals. Moreover, these metrics are generally complex and could not be fully optimized by Lp or conventional adversarial losses.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 28; 2023: 17; 2024: 14; 2025: 17; 2026: 12.

104 papers.

Sort:

By area:

  1. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  2. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  3. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  4. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  5. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
  6. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Modelcited by 52
  7. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
  8. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  9. 2023Separate Anything You Describecited by 43
  10. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  11. 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 36
  12. 2023Novel-View Acoustic Synthesiscited by 33
38 more
  1. 2021Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Featurescited by 32
  2. 2022Cold Diffusion for Speech Enhancementcited by 31
  3. 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognitioncited by 30
  4. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  5. 2021Learning Audio-Visual Dereverberationcited by 26
  6. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  7. 2022RemixIT: Continual self-training of speech enhancement models via bootstrapped remixingcited by 20
  8. 2021MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speechcited by 18
  9. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementcited by 18
  10. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  11. 2022Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancementcited by 14
  12. 2023Self-Supervised Visual Acoustic Matchingcited by 14
  13. 2022Speech Denoising in the Waveform Domain with Self-Attentioncited by 13
  14. 2022SRTNet: Time Domain Speech Enhancement Via Stochastic Refinementcited by 12
  15. 2024The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancementcited by 12
  16. 2021High Fidelity Speech Regeneration with Application to Speech Enhancementcited by 10
  17. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  18. 2024BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embeddingcited by 9
  19. 2022Music Separation Enhancement with Generative Modelingcited by 8
  20. 2022SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Taskscited 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. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  24. 2022Perceptual Contrast Stretching on Target Feature for Speech Enhancementcited by 6
  25. 2022Multi-View Attention Transfer for Efficient Speech Enhancementcited by 6
  26. 2022SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Maskingcited by 6
  27. 2022MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Datacited by 5
  28. 2022Improving Speech Enhancement through Fine-Grained Speech Characteristicscited by 5
  29. 2023Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancementcited by 5
  30. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
  31. 2024DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesiscited by 5
  32. 2022Exploring Self-Attention Mechanisms for Speech Separationcited by 4
  33. 2025xLSTM-SENet: xLSTM for Single-Channel Speech Enhancementcited by 4
  34. 2025A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancementcited by 4
  35. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  36. 2022Blind Restoration of Real-World Audio by 1D Operational GANscited by 3
  37. 2025Linguistic Knowledge Transfer Learning for Speech Enhancementcited by 3
  38. 2026Investigating the Impact of Speech Enhancement on Audio Deepfake Detection in Noisy Environmentscited by 3

50 most cited of 104 All 104 (JSON)