Fetching the paper…

Reading the bibliography…

2024

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

Liu, Mingshuai, Chen, Zhuangqi, Yan, Xiaopeng et al.

Original
PDF
Post on X

Understand

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.

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

Built on

“Fast spectrogram inversion using multi-head convolutional neural networks,”
S. Ö Arık, H. Jun, and G. Diamos, · 2018
Earlier work this paper cites.
“Univnet: A neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation,”
Original
W. Jang, D. Lim, J. Yoon, and others., · 2021
Earlier work this paper cites.

Similar

“S-DCCRN: Super wide band DCCRN with learnable complex feature for speech enhancement,”
S. Lv, Y. Fu, M. Xing, et al., · 2022
Cited alongside, same era.
“Two-stage neural network for icassp 2023 speech signal improvement challenge,”
M. Liu, S. Lv, Z. Zhang, et al., · 2023
Cited alongside, same era.

Then

“Tea-pse 2.0: Sub-band network for real-time personalized speech enhancement,”
Y. Ju, S. Zhang, W. Rao, et al., · 2023
Later among the works it cites.
“Icassp 2023 deep speech enhancement challenge,”
Original
H. Dubey, A. Aazami, V. Gopal, et al., · 2023
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…