Search Results for author: Mingjiang Wang

Found 4 papers, 0 papers with code

Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization

no code implementations9 Jul 2021 Lu Zhang, Mingjiang Wang, Andong Li, Zehua Zhang, Xuyi Zhuang

In this study, we make full use of the contribution of multi-target joint learning to the model generalization capability, and propose a lightweight and low-computing dilated convolutional network (DCN) model for a more robust speech denoising task.

Denoising Speech Denoising +1

Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement

no code implementations9 Jun 2021 Lu Zhang, Mingjiang Wang, Zehua Zhang, Xuyi Zhuang

In this paper, we propose a multi-branch dilated convolutional network (DCN) to simultaneously enhance the magnitude and phase of noisy speech.

Denoising Speech Enhancement

Cannot find the paper you are looking for? You can Submit a new open access paper.