Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain
Sound
2020-11-04 v1 Audio and Speech Processing
Abstract
In low signal-to-noise ratio conditions, it is difficult to effectively recover the magnitude and phase information simultaneously. To address this problem, this paper proposes a two-stage algorithm to decouple the joint optimization problem w.r.t. magnitude and phase into two sub-tasks. In the first stage, only magnitude is optimized, which incorporates noisy phase to obtain a coarse complex clean speech spectrum estimation. In the second stage, both the magnitude and phase components are refined. The experiments are conducted on the WSJ0-SI84 corpus, and the results show that the proposed approach significantly outperforms previous baselines in terms of PESQ, ESTOI, and SDR.
Keywords
Cite
@article{arxiv.2011.01561,
title = {Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain},
author = {Andong Li and Chengshi Zheng and Renhua Peng and Xiaodong Li},
journal= {arXiv preprint arXiv:2011.01561},
year = {2020}
}
Comments
Submitted to ICASSP 2021, 5 pages