# RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement

arXiv: https://arxiv.org/abs/2401.04389 · HTML: https://mlsanity.com/paper/2401.04389/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2024.

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

- [MaskSR: Masked Language Model for Full-band Speech Restoration](https://mlsanity.com/paper/2406.02092/) (2024)
- [TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network](https://mlsanity.com/paper/2505.18533/) (2025)
- [RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention](https://mlsanity.com/paper/2406.07498/) (2024)
- [UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations](https://mlsanity.com/paper/2604.14606/) (2026)

## Abstract (arXiv)

This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-stage network and propose an upgraded model. Specifically, we replace the repairing network with COM-Net from TEA-PSE. In addition, multi-resolution discriminators and multi-band discriminators are adopted in the training stage. Finally, we use a three-step training strategy to optimize our model. We submit two models with different sets of parameters to meet the RTF requirement of the two tracks. According to the official results, the proposed systems rank 2nd in track 1 and 3rd in track 2.