Login / Signup

TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection.

Jie LiuZhiba SuHui HuangCaiYan WanQuanxiu WangJiangli HongBenlai TangFengjie Zhu
Published in: CoRR (2023)
Keyphrases
  • multi frame
  • viewpoint
  • multimedia
  • image sequences
  • reinforcement learning
  • edge detection
  • human motion
  • single frame