Login / Signup

TPTGAN: Two-Path Transformer-Based Generative Adversarial Network Using Joint Magnitude Masking and Complex Spectral Mapping for Speech Enhancement.

Zhaoyi LiuZhuohang JiangWendian LuoZhuoyao FanHaoda DiYufan LongHaizhou Wang
Published in: ICONIP (9) (2023)
Keyphrases
  • speech enhancement
  • linear prediction
  • noise reduction
  • noisy environments
  • image sequences
  • neural network
  • image quality
  • independent component analysis