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

arXiv: https://arxiv.org/abs/2209.11112 · HTML: https://mlsanity.com/paper/2209.11112/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 133 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 30 of 59)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation](https://mlsanity.com/paper/2008.09586/) (2020)
- [Universal Speech Enhancement with Score-based Diffusion](https://mlsanity.com/paper/2206.03065/) (2022)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [A Wavenet for Speech Denoising](https://mlsanity.com/paper/1706.07162/) (2017)
- [CMGAN: Conformer-based Metric GAN for Speech Enhancement](https://mlsanity.com/paper/2203.15149/) (2022)
- [Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM](https://mlsanity.com/paper/1808.05344/) (2018)
- [Neural Vocoder is All You Need for Speech Super-resolution](https://mlsanity.com/paper/2203.14941/) (2022)
- [Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations](https://mlsanity.com/paper/1909.06628/) (2019)

## Built on by (most cited first, 23 of 23)

- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [Universal Speech Enhancement with Regression and Generative Mamba](https://mlsanity.com/paper/2505.21198/) (2025)
- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement](https://mlsanity.com/paper/2505.24576/) (2025)
- [Schr"odinger Bridge Consistency Trajectory Models for Speech Enhancement](https://mlsanity.com/paper/2507.11925/) (2025)
- [UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement](https://mlsanity.com/paper/2510.20441/) (2025)
- [Linguistic Knowledge Transfer Learning for Speech Enhancement](https://mlsanity.com/paper/2503.07078/) (2025)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [Exploiting Time-Frequency Conformers for Music Audio Enhancement](https://mlsanity.com/paper/2308.12599/) (2023)
- [CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR](https://mlsanity.com/paper/2502.20040/) (2025)
- [MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement](https://mlsanity.com/paper/2507.00966/) (2025)
- [Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancement](https://mlsanity.com/paper/2408.06911/) (2024)
- [Investigating training objective for flow matching-based speech enhancement](https://mlsanity.com/paper/2512.10382/) (2025)
- [TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition](https://mlsanity.com/paper/2404.12979/) (2024)
- [VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification](https://mlsanity.com/paper/2502.07205/) (2025)
- [Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch Boosting](https://mlsanity.com/paper/2503.21571/) (2025)
- [A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments](https://mlsanity.com/paper/2506.15000/) (2025)
- [Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy](https://mlsanity.com/paper/2602.00568/) (2026)
- [RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation](https://mlsanity.com/paper/2608.12099/) (2026)
- [Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers](https://mlsanity.com/paper/2608.30329/) (2026)

## 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.