Approximating the maximum of Gaussians by a Gaussian mixture model for statistical designs.
Daiki AzumaShuji TsukiyamaMasahiro FukuiPublished in: ECCTD (2017)
Keyphrases
- gaussian mixture model
- mixture model
- gaussian mixture
- speaker recognition
- feature vectors
- maximum likelihood
- expectation maximization
- em algorithm
- maximum likelihood criterion
- speaker identification
- feature space
- probability density function
- background subtraction
- gaussian mixture modeling
- mixture of gaussians
- density estimation
- data mining
- covariance matrices
- bayesian information criterion
- bayesian networks
- feature extraction