Login / Signup

A Joint Training Framework of Multi-Look Separator and Speaker Embedding Extractor for Overlapped Speech.

Naijun ZhengNa LiBo WuMeng YuJianwei YuChao WengDan SuXunying LiuHelen Meng
Published in: ICASSP (2021)
Keyphrases
  • speech recognition
  • audio visual
  • supervised learning
  • vector space
  • speech signal
  • learning algorithm
  • probabilistic model
  • main contribution
  • training samples