MFCC based Enlargement of the Training Set for Emotion Recognition in Speech.
Inma Mohino-HerranzRoberto Gil-PitaSagrario Alonso-DiazManuel Rosa-ZureraPublished in: CoRR (2014)
Keyphrases
- emotion recognition
- training set
- audio visual
- speaker verification
- emotional speech
- human computer interaction
- test set
- training data
- facial expressions
- data sets
- sentiment analysis
- emotion classification
- speech recognition
- nearest neighbor
- classification accuracy
- information fusion
- facial images
- speech signal
- decision trees
- emotional state
- information retrieval
- multi modal
- acoustic features
- feature extraction
- face images
- affective states
- audio features
- speaker recognition
- test data
- gaussian mixture model
- speaker identification
- multi stream
- speaker diarization
- mel frequency cepstral coefficients
- feature set