# SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping

arXiv: https://arxiv.org/abs/2007.09131 · HTML: https://mlsanity.com/paper/2007.09131/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes](https://mlsanity.com/paper/2205.09248/) (2022)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network](https://mlsanity.com/paper/2103.02147/) (2021)
- [SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking](https://mlsanity.com/paper/2211.12623/) (2022)
- [Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation](https://mlsanity.com/paper/2211.12632/) (2022)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [Deep Neural Mel-Subband Beamformer for In-car Speech Separation](https://mlsanity.com/paper/2211.12590/) (2022)
- [Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation](https://mlsanity.com/paper/2212.05360/) (2022)
- [ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning](https://mlsanity.com/paper/2312.06118/) (2023)
- [A High-Fidelity Speech Super Resolution Network using a Complex Global Attention Module with Spectro-Temporal Loss](https://mlsanity.com/paper/2507.00229/) (2025)
- [VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification](https://mlsanity.com/paper/2502.07205/) (2025)
- [Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling](https://mlsanity.com/paper/2510.26825/) (2025)

## Abstract (arXiv)

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder network with skip connections. In this study, we propose `SkipConvNet' where we replace each skip connection with multiple convolutional modules to provide decoder with intuitive feature maps rather than encoder's output to improve the learning capacity of the network. We also propose the use of optimal smoothing of power spectral density (PSD) as a pre-processing step, which helps to further enhance the efficiency of the network. To evaluate our proposed system, we use the REVERB challenge corpus to assess the performance of various enhancement approaches under the same conditions. We focus solely on monitoring improvements in speech quality and their contribution to improving the efficiency of back-end speech systems, such as speech recognition and speaker verification, trained on only clean speech. Experimental findings show that the proposed system consistently outperforms other approaches.