Divide-and-Conquer based Ensemble to Spot Emotions in Speech using MFCC and Random Forest.
Abdul Malik BadshahJamil AhmadMi Young LeeSung Wook BaikPublished in: CoRR (2016)
Keyphrases
- random forest
- speech recognition
- speech signal
- emotion recognition
- feature set
- random forests
- mel frequency cepstral coefficients
- ensemble methods
- speaker identification
- ensemble learning
- emotional state
- decision trees
- automatic speech recognition
- speaker recognition
- hidden markov models
- base classifiers
- fold cross validation
- ensemble classifier
- audio features
- multi label
- feature extraction
- acoustic features
- rotation forest
- audio visual
- speaker diarization
- non stationary
- facial expressions
- classification accuracy
- feature selection
- benchmark datasets
- feature vectors
- data sets