Parameter estimation for alpha-GMM based on maximum likelihood criterion.

Alpha-integration and alpha-GMM have been recently proposed for integrated stochastic modeling. However, there has not been an approach to date for estimating model parameters for alpha-GMM in a statistical way, based on a set of training data. In this letter, parameter updating formulas are mathematically derived based on maximum likelihood criterion using an adapted expectation-maximization algorithm. With this method, model parameters for alpha-GMM are reestimated in an iterative way. The updating formulas were found to be simple and systematically compatible with the GMM equations. This advantage renders the alpha-GMM a superset of the GMM but with similar computational complexity. This method has been effectively applied to realistic speaker recognition applications.