Lip2Audspec: Speech Reconstruction from Silent Lip Movements Video.
Hassan AkbariHimani AroraLiangliang CaoNima MesgaraniPublished in: ICASSP (2018)
Keyphrases
- visual speech
- lip reading
- visual speech recognition
- mouth region
- motion features
- video analysis
- broadcast news
- video sequences
- video data
- speech recognition
- video streams
- video content
- real time
- video database
- facial features
- high resolution
- noisy environments
- hidden markov models
- audio signals
- audio video
- computer vision
- space time
- multi modal
- digital video
- speech signal
- gaussian mixture model