Loss-Scaled Large-Margin Gaussian Mixture Models for Speech Emotion Classification.
Sungrack YunChang D. YooPublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- gaussian mixture model
- emotion classification
- speaker recognition
- speaker identification
- emotion recognition
- mel frequency cepstral coefficients
- speaker independent
- lexical features
- mixture model
- syntactic analysis
- speaker verification
- sentence level
- feature vectors
- speech recognition
- em algorithm
- novelty detection
- expectation maximization
- maximum likelihood
- feature space
- sentiment analysis
- speech signal
- human computer interaction
- facial expressions
- audio visual
- emotional state
- labeled data
- hidden markov models
- learning algorithm
- model selection
- principal component analysis
- bayesian information criterion
- spectral features
- prior knowledge
- visual features
- support vector
- similarity measure
- feature selection