Login / Signup

FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network.

Zehua ZhangLu ZhangXuyi ZhuangYukun QianHeng LiMingjiang Wang
Published in: ICASSP (2022)
Keyphrases
  • single channel
  • speech enhancement
  • optical flow
  • wavelet transform
  • edge detection
  • synthetic and real images
  • multiscale
  • multi channel