Junyu Wang — accepted AI-conference papers

2025

Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement

Junyu Wang, Zizhen Lin, Tianrui Wang, Meng Ge, Longbiao Wang, Jianwu Dang

ICASSP 2025accepted

In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment. Mamba, as a novel state-space model (SSM), has gained widespr…

Cited by 0 Source ↗Scholar ↗

2025

PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement

Zizhen Lin, Junyu Wang, Ruili Li, Fei Shen, Xi Xuan

ICASSP 2025accepted

Single-channel speech enhancement is a challenging ill-posed problem focused on estimating clean speech from degraded signals. Existing studies have demonstrated the competitive performance of combining convolutional neural networks (CNNs) with Transformers in speech enhancement tasks. However, exis…

Cited by 16 Source ↗Scholar ↗