# DESNet: A Multi-channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation

arXiv: https://arxiv.org/abs/2011.02131 · HTML: https://mlsanity.com/paper/2011.02131/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [Hardware and Software Platform Inference](https://mlsanity.com/paper/2411.05197/) (2024)
- [Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain](https://mlsanity.com/paper/2206.15423/) (2022)
- [Distil-DCCRN: A Small-footprint DCCRN Leveraging Feature-based Knowledge Distillation in Speech Enhancement](https://mlsanity.com/paper/2408.04267/) (2024)
- [Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation](https://mlsanity.com/paper/2205.08455/) (2022)
- [Learning Filterbanks for End-to-End Acoustic Beamforming](https://mlsanity.com/paper/2111.04614/) (2021)
- [IRCNN+: An Enhanced Iterative Residual Convolutional Neural Network for Non-stationary Signal Decomposition](https://mlsanity.com/paper/2309.04782/) (2023)

## Abstract (arXiv)

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the multi-channel features, which is originally proposed in end-to-end unmixing, fixed-beamforming and extraction (E2E-UFE) structure. Furthermore, the novel deep complex convolutional recurrent network (DCCRN) is used as the structure of the speech unmixing and the neural network based weighted prediction error (WPE) is cascaded beforehand for speech dereverberation. We also introduce the staged SNR strategy and symphonic loss for the training of the network to further improve the final performance. Experiments show that in non-dereverberated case, the proposed DESNet outperforms DCCRN and most state-of-the-art structures in speech enhancement and separation, while in dereverberated scenario, DESNet also shows improvements over the cascaded WPE-DCCRN networks.