Login / Signup

EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers.

Yushi UedaSoumi MaitiShinji WatanabeChunlei ZhangMeng YuShi-Xiong ZhangYong Xu
Published in: CoRR (2022)
Keyphrases
  • end to end
  • speech recognition
  • speaker diarization
  • neural network
  • image sequences
  • computational complexity
  • maximum likelihood
  • admission control