# On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems

arXiv: https://arxiv.org/abs/2007.14974 · HTML: https://mlsanity.com/paper/2007.14974/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement](https://mlsanity.com/paper/2110.06467/) (2021)
- [Synthesizing Iris Images using Generative Adversarial Networks: Survey and Comparative Analysis](https://mlsanity.com/paper/2404.17105/) (2024)
- [Exploring Self-Attention Mechanisms for Speech Separation](https://mlsanity.com/paper/2202.02884/) (2022)
- [Time-domain Speech Enhancement with Generative Adversarial Learning](https://mlsanity.com/paper/2103.16149/) (2021)
- [A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement](https://mlsanity.com/paper/2109.02011/) (2021)
- [ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning](https://mlsanity.com/paper/2312.06118/) (2023)

## Abstract (arXiv)

Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches. Additionally, many loss functions have been proposed for GAN-based approaches, but they have not been adequately compared. In this study, we propose novel convolutional recurrent GAN (CRGAN) architectures for speech enhancement. Multiple loss functions are adopted to enable direct comparisons to other GAN-based systems. The benefits of including recurrent layers are also explored. Our results show that the proposed CRGAN model outperforms the SOTA GAN-based models using the same loss functions and it outperforms other non-GAN based systems, indicating the benefits of using a GAN for speech enhancement. Overall, the CRGAN model that combines an objective metric loss function with the mean squared error (MSE) provides the best performance over comparison approaches across many evaluation metrics.