# Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification

arXiv: https://arxiv.org/abs/1709.01703 · HTML: https://mlsanity.com/paper/1709.01703/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2017.

## Built on by (most cited first, 19 of 19)

- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (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)
- [Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport](https://mlsanity.com/paper/2111.06316/) (2021)
- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [Perceptual Contrast Stretching on Target Feature for Speech Enhancement](https://mlsanity.com/paper/2203.17152/) (2022)
- [SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking](https://mlsanity.com/paper/2211.12623/) (2022)
- [A Survey of Deep Learning Audio Generation Methods](https://mlsanity.com/paper/2406.00146/) (2024)
- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [Linguistic Knowledge Transfer Learning for Speech Enhancement](https://mlsanity.com/paper/2503.07078/) (2025)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement](https://mlsanity.com/paper/2507.00966/) (2025)
- [A Unified View of cGANs with and without Classifiers](https://mlsanity.com/paper/2111.01035/) (2021)
- [Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification](https://mlsanity.com/paper/2102.02074/) (2021)
- [SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points](https://mlsanity.com/paper/2111.04436/) (2021)
- [Model Joins: Enabling Analytics Over Joins of Absent Big Tables](https://mlsanity.com/paper/2206.10434/) (2022)
- [Self-supervised learning with diffusion-based multichannel speech enhancement for speaker verification under noisy conditions](https://mlsanity.com/paper/2307.02244/) (2023)
- [Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement](https://mlsanity.com/paper/2510.01958/) (2025)

## Abstract (arXiv)

Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of conditional GANs (cGANs) for SE, and in particular, we make use of the image processing framework proposed by Isola et al. [1] to learn a mapping from the spectrogram of noisy speech to an enhanced counterpart. The SE cGAN consists of two networks, trained in an adversarial manner: a generator that tries to enhance the input noisy spectrogram, and a discriminator that tries to distinguish between enhanced spectrograms provided by the generator and clean ones from the database using the noisy spectrogram as a condition. We evaluate the performance of the cGAN method in terms of perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and equal error rate (EER) of speaker verification (an example application). Experimental results show that the cGAN method overall outperforms the classical short-time spectral amplitude minimum mean square error (STSA-MMSE) SE algorithm, and is comparable to a deep neural network-based SE approach (DNN-SE).