Audio head pose estimation using the direct to reverberant speech ratio.
Mark BarnardWenwu WangPublished in: Speech Commun. (2016)
Keyphrases
- head pose estimation
- speech signal
- pose estimation
- manifold embedding
- tracking and pose estimation
- emotion recognition
- speech recognition
- manifold learning
- visual tracking
- facial expressions
- subspace learning
- random forests
- facial features
- signal processing
- head motion
- machine learning
- gaze estimation
- depth images
- pose variations
- hidden markov models
- viewpoint
- high quality