Dynamic Sliding Window for Realtime Denoising Networks

Jinxu Xiang; Yuyang Zhu; Rundi Wu; Ruilin Xu; Yuko Ishiwaka; Changxi Zheng

ICASSP 2022accepted0 citations

Dynamic Sliding Window for Realtime Denoising Networks

Jinxu Xiang, Yuyang Zhu, Rundi Wu, Ruilin Xu, Yuko Ishiwaka, Changxi Zheng

Abstract

Realtime speech denoising has been long studied. Almost all existing methods process the incoming data stream using a sliding window of fixed-size. Yet, we show that the use of fixed-size sliding window may lead to an accumulating lag, especially in presence of other background computing processes that may occupy CPU resources. In response, we propose a new sliding window strategy and a lightweight neural network to leverage it. Our experiments show that the proposed approach achieves denoising quality on a par with the stateof-the-art realtime denoising models. More importantly, our approach is faster, maintaining a stable realtime performance even when the available computing power fluctuates.

BibTeX

@inproceedings{icassp2022_dynamicslidingwi,
  title = {Dynamic Sliding Window for Realtime Denoising Networks},
  author = {Jinxu Xiang and Yuyang Zhu and Rundi Wu and Ruilin Xu and Yuko Ishiwaka and Changxi Zheng},
  booktitle = {ICASSP 2022},
  year = {2022}
}