# MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data

arXiv: https://arxiv.org/abs/2203.12369 · HTML: https://mlsanity.com/paper/2203.12369/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 23 Mar 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [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)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM](https://mlsanity.com/paper/1808.05344/) (2018)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks](https://mlsanity.com/paper/1709.03658/) (2017)
- [Spectral feature mapping with mimic loss for robust speech recognition](https://mlsanity.com/paper/1803.09816/) (2018)
- [Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet](https://mlsanity.com/paper/2111.03847/) (2021)
- [Deep Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement](https://mlsanity.com/paper/2011.10345/) (2020)
- [Deep Noise Suppression With Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data](https://mlsanity.com/paper/2103.17088/) (2021)
- [Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASR](https://mlsanity.com/paper/1811.11517/) (2018)

## Built on by (most cited first, 5 of 5)

- [Perceive and predict: self-supervised speech representation based loss functions for speech enhancement](https://mlsanity.com/paper/2301.04388/) (2023)
- [Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation](https://mlsanity.com/paper/2205.08455/) (2022)
- [Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations](https://mlsanity.com/paper/2307.13423/) (2023)
- [The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions](https://mlsanity.com/paper/2307.14502/) (2023)
- [WhiSQA: Non-Intrusive Speech Quality Prediction Using Whisper Encoder Features](https://mlsanity.com/paper/2508.02210/) (2025)

## Abstract (arXiv)

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training via a predictor network has recently gained interest. However, the performance of such predictors is limited by the distribution of metric scores that appear in the training data. In this work, we propose MetricGAN+/- (an extension of MetricGAN+, one such metric-motivated system) which introduces an additional network - a "de-generator" which attempts to improve the robustness of the prediction network (and by extension of the generator) by ensuring observation of a wider range of metric scores in training. Experimental results on the VoiceBank-DEMAND dataset show relative improvement in PESQ score of 3.8% (3.05 vs 3.22 PESQ score), as well as better generalisation to unseen noise and speech.