On Robustness to Missing Video for Audiovisual Speech Recognition.
Oscar ChangOtavio BragaHank LiaoDmitriy SerdyukOlivier SiohanPublished in: Trans. Mach. Learn. Res. (2022)
Keyphrases
- speech recognition
- video retrieval
- hidden markov models
- language model
- automatic speech recognition
- digital video library
- speech signal
- speech recognizer
- speech synthesis
- speech understanding
- video clips
- video data
- speaker identification
- pattern recognition
- speech processing
- video content
- noisy environments
- multimedia
- speech recognition technology
- video database
- video streams
- video sequences
- speaker dependent
- video frames
- speech recognition systems
- key frames
- signal processing
- neural network
- video analysis
- visual features
- visual information
- video shots
- speaker adaptation
- multimedia content
- speech recognition errors
- audio visual
- speech recognizers
- isolated word
- audio visual speech recognition
- visual data