Monaural speech enhancement with complex convolutional block attention module and joint time frequency losses

Notes
papers
ai

(Zhao, Nguyen, and Ma 2021)

Notes {#notes}

ABSTRACT {#abstract}

  • Deep Complex U-Net and CRN achieved SOTA performance for monaural speech enhancement
  • both are encoder decoder structures with skip connections

Bibliography {#bibliography}

Zhao, Shengkui, Trung Hieu Nguyen, and Bin Ma. 2021. “Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses.” CoRR. http://arxiv.org/abs/2102.01993v1.