Login / Signup

Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data.

Junyi AoZiqiang ZhangLong ZhouShujie LiuHaizhou LiTom KoLirong DaiJinyu LiYao QianFuru Wei
Published in: CoRR (2022)
Keyphrases
  • end to end
  • network structure
  • real world
  • speech recognition
  • ad hoc networks
  • automatic speech recognition
  • network bandwidth
  • admission control