A generalized family of parameter estimation techniques

The Extended Baum-Welch (EBW) Transformations is one of a variety of techniques to estimate parameters of Gaussian mixture models. In this paper, we provide a theoretical framework for general parameter estimation and show the relationship between these different approaches. Namely, we introduce a general family of model parameter updates that generalizes a Baum-Welch (BW) recursive process to an arbitrary objective function of Gaussian Mixture Models, and show how other commonly used parameter estimation techniques belong to this family of model update rules. We present a linearlized formulation that allows for the construction of an even more general family of update rules with any specified value for the gradient that measures how much an initial model is moved to an estimated updated model.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Dimitri Kanevsky, Tara N. Sainath, Bhuvana Ramabhadran
• Keywords: Gaussian Mixture Models, General Parameter Estimation, ICASSP 2009, Parameter Estimation, Signal Processing