Login / Signup

Efficient Multi-angle Audio-visual Speech Recognition using Parallel WaveGAN based Scene Classifier.

Shinnosuke IsobeSatoshi TamuraYuuto GotohMasaki Nose
Published in: ICPRAM (2022)
Keyphrases
  • visual speech
  • visual data
  • d scene
  • feature selection
  • audio visual speech recognition
  • multimedia
  • image sequences
  • dynamic scenes
  • audio signal
  • video sequences
  • wavelet transform
  • multi modal
  • speaker identification