Optimal on-line Bayesian model selection for speaker adaptation

In this paper, we show how to accomodate a Bayesian variant of Rissanen’s MDL into on-line Bayesian adaptation to control both model structural complexity and parameterization complexity to best fit an available amount of adaptation data, the goal being minimization of resulting recognition error. An efficient bottom-up dynamic programming based pruning algorithm is developed for selecting models using the MDL principle. Speaker adaptation experiments using a 26-letter English alphabet vocabulary were conducted and the proposed Bayesian variant MDL method is shown to provide an optimal tradeoff between recognition accuracy and complexity of model structure and parameterization over a full range of adaptation data size. It in general is capable of automaticlly selecting a set of model parameters that leads to best recognition performance for a given amount of adaptation data.