Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakes.
Pavel KorshunovHaolin ChenPhilip N. GarnerSébastien MarcelPublished in: CoRR (2023)
Keyphrases
- audio visual
- multi modal
- visual information
- multi stream
- emotion recognition
- visual data
- pattern recognition
- temporal context
- object recognition
- multimedia
- audio visual speech recognition
- person authentication
- data sets
- audio features
- human activities
- activity recognition
- domain knowledge
- hidden markov models
- feature extraction