Login / Signup

Robust Audio-Visual ASR with Unified Cross-Modal Attention.

Jiahong LiChenda LiYifei WuYanmin Qian
Published in: ICASSP (2023)
Keyphrases
  • audio visual
  • cross modal
  • multi modal
  • visual data
  • multimedia
  • visual information
  • high dimensional
  • noisy environments
  • multimedia retrieval
  • data sets
  • search engine
  • high dimensional data
  • visual similarity