Speaker adaptation using constrained estimation of Gaussian mixtures.
Vassilios DigalakisDimitry RtischevLeonardo NeumeyerPublished in: IEEE Trans. Speech Audio Process. (1995)
Keyphrases
- gaussian mixture
- density estimation
- speaker adaptation
- em algorithm
- gaussian mixture model
- expectation maximization
- probability density function
- maximum likelihood
- closed form
- speech recognition
- covariance matrix
- pattern recognition
- maximum likelihood estimation
- neural network
- parameter estimation
- machine learning
- objective function
- image processing
- multiscale
- prior knowledge
- feature space
- video sequences