# Improving GANs for Speech Enhancement

arXiv: https://arxiv.org/abs/2001.05532 · HTML: https://mlsanity.com/paper/2001.05532/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2020.

## Built on by (most cited first, 22 of 22)

- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [Universal Speech Enhancement with Score-based Diffusion](https://mlsanity.com/paper/2206.03065/) (2022)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [A Study on Speech Enhancement Based on Diffusion Probabilistic Model](https://mlsanity.com/paper/2107.11876/) (2021)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [Speech Denoising in the Waveform Domain with Self-Attention](https://mlsanity.com/paper/2202.07790/) (2022)
- [SRTNet: Time Domain Speech Enhancement Via Stochastic Refinement](https://mlsanity.com/paper/2210.16805/) (2022)
- [Metric-oriented Speech Enhancement using Diffusion Probabilistic Model](https://mlsanity.com/paper/2302.11989/) (2023)
- [DDTSE: Discriminative Diffusion Model for Target Speech Extraction](https://mlsanity.com/paper/2309.13874/) (2023)
- [A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement](https://mlsanity.com/paper/2206.11000/) (2022)
- [A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition](https://mlsanity.com/paper/2405.16952/) (2024)
- [Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain](https://mlsanity.com/paper/2110.04791/) (2021)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [Blind Restoration of Real-World Audio by 1D Operational GANs](https://mlsanity.com/paper/2212.14618/) (2022)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [Speech Enhancement for Wake-Up-Word detection in Voice Assistants](https://mlsanity.com/paper/2101.12732/) (2021)
- [Complex Image-Generative Diffusion Transformer for Audio Denoising](https://mlsanity.com/paper/2406.09161/) (2024)
- [Selective State Space Model for Monaural Speech Enhancement](https://mlsanity.com/paper/2411.06217/) (2024)
- [Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching](https://mlsanity.com/paper/2506.16127/) (2025)
- [Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU](https://mlsanity.com/paper/2105.02509/) (2021)
- [Enhancing Gappy Speech Audio Signals with Generative Adversarial Networks](https://mlsanity.com/paper/2305.05780/) (2023)
- [RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior](https://mlsanity.com/paper/2502.13574/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement mapping. In this work, we propose to use multiple generators that are chained to perform multi-stage enhancement mapping, which gradually refines the noisy input signals in a stage-wise fashion. Furthermore, we study two scenarios: (1) the generators share their parameters and (2) the generators' parameters are independent. The former constrains the generators to learn a common mapping that is iteratively applied at all enhancement stages and results in a small model footprint. On the contrary, the latter allows the generators to flexibly learn different enhancement mappings at different stages of the network at the cost of an increased model size. We demonstrate that the proposed multi-stage enhancement approach outperforms the one-stage SEGAN baseline, where the independent generators lead to more favorable results than the tied generators. The source code is available at http://github.com/pquochuy/idsegan.