# KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge

arXiv: https://arxiv.org/abs/2402.01808 · HTML: https://mlsanity.com/paper/2402.01808/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2024.

## Built on by (most cited first, 5 of 5)

- [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)
- [Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement](https://mlsanity.com/paper/2508.20859/) (2025)
- [Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns](https://mlsanity.com/paper/2509.05079/) (2025)
- [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 presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a generative adversarial network (GAN) in complex-domain for speech restoration and a fine-grained multi-band fusion module for speech enhancement. In the blind test set of SSI, the proposed system achieves an overall mean opinion score (MOS) of 3.49 based on ITU-T P.804 and a Word Accuracy Rate (WAcc) of 0.78 for the real-time track, as well as an overall P.804 MOS of 3.43 and a WAcc of 0.78 for the non-real-time track, ranking 1st in both tracks.