On Robustness to Missing Video for Audiovisual Speech Recognition.
Oscar ChangOtavio BragaHank LiaoDmitriy SerdyukOlivier SiohanPublished in: CoRR (2023)
Keyphrases
- speech recognition
- hidden markov models
- digital video library
- video retrieval
- speech processing
- pattern recognition
- automatic speech recognition
- language model
- video data
- speech synthesis
- video clips
- speech recognizer
- video content
- speaker identification
- video frames
- noisy environments
- video streams
- speech understanding
- speech recognition systems
- speech signal
- video database
- video analysis
- multimedia
- speaker independent
- speaker dependent
- multimedia content
- video sequences
- speech recognition technology
- video search
- speaker diarization
- speech recognition errors
- machine learning
- audio visual
- multi modal
- low level
- speaker adaptation
- cepstral coefficients