Acoustic emotion recognition based on fusion of multiple feature-dependent deep Boltzmann machines.
Kelvin Poon-FengDong-Yan HuangMinghui DongHaizhou LiPublished in: ISCSLP (2014)
Keyphrases
- multiple features
- emotion recognition
- emotional speech
- data fusion
- information fusion
- audio visual
- facial expressions
- visual information
- feature space
- metric learning
- feature set
- combining multiple
- relevance feedback
- feature vectors
- image retrieval
- incremental learning
- low level features
- multiple instance learning
- emotional state
- class labels
- data sets
- low level
- keywords
- training data
- feature extraction
- face recognition
- data mining