Login / Signup

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR.

Hirofumi InagumaTatsuya Kawahara
Published in: Interspeech (2021)
Keyphrases
  • automatic speech recognition
  • probability distribution
  • visual attention
  • real time
  • speech recognition
  • multimedia
  • video sequences
  • response time
  • vision system
  • selection algorithm
  • low latency