Audio-Visual Efficient Conformer for Robust Speech Recognition.
Maxime BurchiRadu TimoftePublished in: WACV (2023)
Keyphrases
- speech recognition
- audio visual speech recognition
- audio visual
- noisy environments
- multi stream
- multi modal
- speaker verification
- language model
- hidden markov models
- automatic speech recognition
- pattern recognition
- speech synthesis
- visual information
- speech signal
- digit recognition
- speech recognition systems
- computer vision
- speech recognizer
- multimedia
- visual data
- noise reduction
- bayesian networks
- speaker independent