title: EXTENDED BAUM TRANSFORMATIONS FOR GENERAL FUNCTIONS, II creator: Kanevsky, Dr Dimitri subject: Statistical Models description: The discrimination technique for estimating the parameters of Gaussian mixtures that is based on the Extended Baum transformations (EB) has had significant impact on the speech recognition community. The proof that definitively shows that these transformations increase the value of an objective function with iteration (i.e., so-called "growth transformations") was presented by the author two years ago for a diagonal Gaussian mixture densities. In this paper this proof is extended to a multidimensional multivariate Gaussian mixtures. The proof presented in the current paper is based on the linearization process and the explicit growth estimate for linear forms of Gaussian mixtures. date: 2005-06 type: Departmental Technical Report type: NonPeerReviewed format: application/pdf identifier: http://cogprints.org/5058/1/rc23645.pdf identifier: Kanevsky, Dr Dimitri (2005) EXTENDED BAUM TRANSFORMATIONS FOR GENERAL FUNCTIONS, II. [Departmental Technical Report] (Unpublished) relation: http://cogprints.org/5058/