Login / Signup

MossFormer: Pushing the Performance Limit of Monaural Speech Separation Using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions.

Shengkui ZhaoBin Ma
Published in: ICASSP (2023)
Keyphrases
  • image processing
  • speech recognition
  • real time
  • information retrieval
  • scale space
  • fault diagnosis
  • recognition engine