Audio-visual speaker conversion using prosody features.
Adela BarbulescuThomas HueberGérard BaillyRémi RonfardPublished in: AVSP (2013)
Keyphrases
- audio visual
- person authentication
- multi modal
- audio features
- visual information
- multimodal fusion
- speaker verification
- multi stream
- visual data
- multimedia
- emotion recognition
- audio visual speech recognition
- image features
- low level
- feature vectors
- feature extraction
- feature set
- co occurrence
- hidden markov models
- feature space
- data analysis
- three dimensional