Face-Mic: inferring live speech and speaker identity via subtle facial dynamics captured by AR/VR motion sensors.
Cong ShiXiangyu XuTianfang ZhangPayton WalkerYi WuJian LiuNitesh SaxenaYingying ChenJiadi YuPublished in: MobiCom (2021)
Keyphrases
- facial motion
- facial expressions
- speech recognition
- human faces
- facial animation
- hidden markov models
- facial images
- video sequences
- face images
- augmented reality
- automatic speech recognition
- audio visual
- speaker verification
- virtual reality
- facial recognition
- emotion recognition
- real time
- speaker recognition
- recognition engine
- facial features
- speaker identification
- head motion
- visual speech
- facial expression recognition
- expression recognition
- automatic speech recognition systems
- face model
- face recognition
- speech signal
- facial gestures
- facial appearance
- facial muscles
- prosodic features
- face analysis
- robot motion
- facial actions
- vocal tract
- speaker diarization
- moving objects
- speaker dependent
- optical flow
- speaker independent
- virtual world
- human computer interaction
- visual data
- head movements
- speech synthesis
- virtual environment
- acoustic features
- feature points
- language model
- gaussian mixture model
- broadcast news
- synthesized speech
- face region