Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain
arXiv:2011.01561
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.
Submitted to ICASSP 2021, 5 pages
Cited by in corpus (4)
- A Simultaneous Denoising and Dereverberation Framework with Target Decoupling
- Speech Enhancement Using Multi-Stage Self-Attentive Temporal Convolutional Networks
- Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization
- Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement