# DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network for Speech Enhancement

arXiv: https://arxiv.org/abs/2012.10732 · HTML: https://mlsanity.com/paper/2012.10732/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Complex Image Generation SwinTransformer Network for Audio Denoising](https://mlsanity.com/paper/2310.16109/) (2023)
- [DPATD: Dual-Phase Audio Transformer for Denoising](https://mlsanity.com/paper/2310.19588/) (2023)
- [Diffusion Gaussian Mixture Audio Denoise](https://mlsanity.com/paper/2406.09154/) (2024)
- [Complex Image-Generative Diffusion Transformer for Audio Denoising](https://mlsanity.com/paper/2406.09161/) (2024)

## Abstract (arXiv)

Generative adversarial network (GAN) still exists some problems in dealing with speech enhancement (SE) task. Some GAN-based systems adopt the same structure from Pixel-to-Pixel directly without special optimization. The importance of the generator network has not been fully explored. Other related researches change the generator network but operate in the time-frequency domain, which ignores the phase mismatch problem. In order to solve these problems, a deep complex convolution recurrent GAN (DCCRGAN) structure is proposed in this paper. The complex module builds the correlation between magnitude and phase of the waveform and has been proved to be effective. The proposed structure is trained in an end-to-end way. Different LSTM layers are used in the generator network to sufficiently explore the speech enhancement performance of DCCRGAN. The experimental results confirm that the proposed DCCRGAN outperforms the state-of-the-art GAN-based SE systems.