# MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech

arXiv: https://arxiv.org/abs/2110.05866 · HTML: https://mlsanity.com/paper/2110.05866/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 12 Oct 2021.

## Builds on (most cited first, 15 of 15)

- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [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)
- [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)
- [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)
- [Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders](https://mlsanity.com/paper/2106.12271/) (2021)
- [An Open source Implementation of ITU-T Recommendation P.808 with Validation](https://mlsanity.com/paper/2005.08138/) (2020)
- [Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech](https://mlsanity.com/paper/2101.08625/) (2021)
- [CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism](https://mlsanity.com/paper/2107.13143/) (2021)
- [Noise Tokens: Learning Neural Noise Templates for Environment-Aware Speech Enhancement](https://mlsanity.com/paper/2004.04001/) (2020)
- [iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning](https://mlsanity.com/paper/2004.00932/) (2020)
- [Deep Noise Suppression With Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data](https://mlsanity.com/paper/2103.17088/) (2021)
- [TENET: A Time-reversal Enhancement Network for Noise-robust ASR](https://mlsanity.com/paper/2107.01531/) (2021)

## Built on by (most cited first, 18 of 18)

- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Self-Supervised Visual Acoustic Matching](https://mlsanity.com/paper/2307.15064/) (2023)
- [Perceive and predict: self-supervised speech representation based loss functions for speech enhancement](https://mlsanity.com/paper/2301.04388/) (2023)
- [Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech](https://mlsanity.com/paper/2402.16321/) (2024)
- [SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning](https://mlsanity.com/paper/2402.16830/) (2024)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations](https://mlsanity.com/paper/2307.13423/) (2023)
- [Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data](https://mlsanity.com/paper/2405.19497/) (2024)
- [A Hybrid Model for Weakly-Supervised Speech Dereverberation](https://mlsanity.com/paper/2502.06839/) (2025)
- [WhiSQA: Non-Intrusive Speech Quality Prediction Using Whisper Encoder Features](https://mlsanity.com/paper/2508.02210/) (2025)
- [A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech](https://mlsanity.com/paper/2210.15368/) (2022)
- [Speech Modeling with a Hierarchical Transformer Dynamical VAE](https://mlsanity.com/paper/2303.09404/) (2023)
- [Unsupervised speech enhancement with deep dynamical generative speech and noise models](https://mlsanity.com/paper/2306.07820/) (2023)
- [Autoregressive Speech Enhancement via Acoustic Tokens](https://mlsanity.com/paper/2507.12825/) (2025)
- [Integrating Uncertainty into Neural Network-based Speech Enhancement](https://mlsanity.com/paper/2305.08744/) (2023)
- [U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model](https://mlsanity.com/paper/2507.14237/) (2025)
- [Unsupervised Speech Enhancement using Data-defined Priors](https://mlsanity.com/paper/2509.22942/) (2025)

## Abstract (arXiv)

Most of the deep learning-based speech enhancement models are learned in a supervised manner, which implies that pairs of noisy and clean speech are required during training. Consequently, several noisy speeches recorded in daily life cannot be used to train the model. Although certain unsupervised learning frameworks have also been proposed to solve the pair constraint, they still require clean speech or noise for training. Therefore, in this paper, we propose MetricGAN-U, which stands for MetricGAN-unsupervised, to further release the constraint from conventional unsupervised learning. In MetricGAN-U, only noisy speech is required to train the model by optimizing non-intrusive speech quality metrics. The experimental results verified that MetricGAN-U outperforms baselines in both objective and subjective metrics.