Login / Signup

Hourglass-AVSR: Down-Up Sampling-Based Computational Efficiency Model for Audio-Visual Speech Recognition.

Fan YuHaoxu WangZiyang MaShiliang Zhang
Published in: ICASSP (2024)
Keyphrases
  • computational efficiency
  • probabilistic model
  • information retrieval
  • metadata
  • high level
  • pattern recognition
  • information retrieval systems
  • multi modal
  • computationally efficient
  • audio visual