no code implementations • 2 Aug 2022 • Jun Xue, Cunhang Fan, Zhao Lv, JianHua Tao, Jiangyan Yi, Chengshi Zheng, Zhengqi Wen, Minmin Yuan, Shegang Shao
Meanwhile, to make full use of the phase and full-band information, we also propose to use real and imaginary spectrogram features as complementary input features and model the disjoint subbands separately.
no code implementations • 14 Feb 2022 • Chengshi Zheng, Wenzhe Liu, Andong Li, Yuxuan Ke, XiaoDong Li
To improve the performance of traditional low-latency speech enhancement algorithms, a deep filter-bank equalizer (FBE) framework was proposed, which integrated a deep learning-based subband noise reduction network with a deep learning-based shortened digital filter mapping network.
no code implementations • 3 Feb 2022 • Linjuan Cheng, Chengshi Zheng, Andong Li, Yuquan Wu, Renhua Peng, XiaoDong Li
In hands-free communication system, the coupling between loudspeaker and microphone generates echo signal, which can severely influence the quality of communication.
1 code implementation • 13 Oct 2021 • Guochen Yu, Andong Li, Chengshi Zheng, Yinuo Guo, Yutian Wang, Hui Wang
Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance.
no code implementations • 5 Sep 2021 • Guochen Yu, Yutian Wang, Hui Wang, Qin Zhang, Chengshi Zheng
After that, the second stage is applied to further suppress the residual noise components and estimate the clean phase by a complex spectral mapping network, which is a pure complex-valued network composed of complex 2D convolution/deconvolution and complex temporal-frequency attention blocks.
no code implementations • 19 Feb 2021 • Weixin Meng, Chengshi Zheng, XiaoDong Li
The proposed beamformer can be regarded as a generalization of the minimum power distortionless response beamformer and its improved variations.