2 papers
cs.SD2024
MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement
Zizhen Lin, Xiaoting Chen, Junyu Wang
Achieving a balance between lightweight design and high performance remains a challenging task for speech enhancement. In this paper, we introduce Multi-path Enhanced Taylor (MET)…
eess.AS2023
An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention
Junyu Wang
We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited recep…