RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要