Speech emotion recognition based on Gaussian Mixture Models and Deep Neural Networks.
Ivan J. TashevZhong-Qiu WangKeith W. GodinPublished in: ITA (2017)
Keyphrases
- gaussian mixture model
- speech emotion recognition
- neural network
- mixture model
- speaker recognition
- em algorithm
- expectation maximization
- maximum likelihood
- pattern recognition
- probability density
- artificial neural networks
- feature space
- feature vectors
- gaussian mixture
- density estimation
- speaker identification
- covariance matrices
- neural network model
- variational bayes
- gaussian distribution
- multilayer perceptron
- self organizing maps
- probability density function
- bayesian information criterion
- generative model
- decision trees
- information retrieval
- training data