Knowledge Network Node
Radio Engineering. Core
Version after Accepted▼
(Accepted Version) Online First Publishing Date: 2023-09-04 10:24:30

Multi-channel Speech Enhancement Based on Fourier ConvolutionChinese Full Text

SUN Siyu;ZHANG Haijian;CHEN Jiajia;

Abstract: The construction of neural beamformer is one of the main methods to deal with multi-channel speech enhancement tasks， which filters the multi-channel signals to obtain target speech by solving beam weights. Similar to the principle of the solution of the spatial covariance matrix in traditional beamforming， spectral-spatial information also plays crucial roles in beam weights prediction. However， due to the lack of adequate learning of spectral-spatial cues， many existing works fails to optimall... More
Keywords：

Multi-channel; speech enhancement; neural beamformer; Fourier convolution; deep learning;

  • Series：

    (I) Electronic Technology ＆ Information Science

  • Subject：

    Telecom Technology

  • Classification Code：

    TN912.35

CNKI exclusive online-first articles is prohibited to reprint and excerpt without permission.

Download the mobile appuse the app to scan this coderead the article.

Tips: Please download CAJViewer to view CAJ format full text.

Download: 126 Pagecount: 10 Size: 587K

Related Literature
  • Similar Article
  • Reader Recommendation
  • Associated Author