Neural processing of degraded speech using speaker's mouth movement.
Tomomi Mizuochi-EndoMichiru MakuuchiPublished in: AVSP (2019)
Keyphrases
- speech recognition
- audio visual
- speaker recognition
- automatic speech recognition
- speaker verification
- speaker identification
- visual speech
- prosodic features
- speaker diarization
- neural network
- speaker dependent
- automatic speech recognition systems
- network architecture
- data processing
- speech signal
- speech synthesis
- information processing
- pattern recognition
- real time
- acoustic features
- hidden markov models
- recognition engine
- image restoration
- broadcast news
- neural model
- gaussian mixture model
- language model
- mel frequency cepstral coefficients
- lip reading
- image sequences