# Complex Image Generation SwinTransformer Network for Audio Denoising

arXiv: https://arxiv.org/abs/2310.16109 · HTML: https://mlsanity.com/paper/2310.16109/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [Mixed Transformer U-Net For Medical Image Segmentation](https://mlsanity.com/paper/2111.04734/) (2021)
- [Phase-aware Speech Enhancement with Deep Complex U-Net](https://mlsanity.com/paper/1903.03107/) (2019)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [MANNER: Multi-view Attention Network for Noise Erasure](https://mlsanity.com/paper/2203.02181/) (2022)
- [A Fully Convolutional Neural Network for Speech Enhancement](https://mlsanity.com/paper/1609.07132/) (2016)
- [Convolutional-Recurrent Neural Networks for Speech Enhancement](https://mlsanity.com/paper/1805.00579/) (2018)
- [Speech Denoising Without Clean Training Data: A Noise2Noise Approach](https://mlsanity.com/paper/2104.03838/) (2021)
- [A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings](https://mlsanity.com/paper/2202.08702/) (2022)
- [S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement](https://mlsanity.com/paper/2111.08387/) (2021)
- [Speech Denoising in the Waveform Domain with Self-Attention](https://mlsanity.com/paper/2202.07790/) (2022)
- [Speech enhancement with weakly labelled data from AudioSet](https://mlsanity.com/paper/2102.09971/) (2021)
- [BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds](https://mlsanity.com/paper/2210.10196/) (2022)
- [DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network for Speech Enhancement](https://mlsanity.com/paper/2012.10732/) (2020)
- [Deep Denoising for Hearing Aid Applications](https://mlsanity.com/paper/1805.01198/) (2018)
- [Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition](https://mlsanity.com/paper/1611.07174/) (2016)

## Built on by (most cited first, 3 of 3)

- [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)

Achieving high-performance audio denoising is still a challenging task in real-world applications. Existing time-frequency methods often ignore the quality of generated frequency domain images. This paper converts the audio denoising problem into an image generation task. We first develop a complex image generation SwinTransformer network to capture more information from the complex Fourier domain. We then impose structure similarity and detailed loss functions to generate high-quality images and develop an SDR loss to minimize the difference between denoised and clean audios. Extensive experiments on two benchmark datasets demonstrate that our proposed model is better than state-of-the-art methods.