Boosting long-term adaptation of hidden-Markov-models: incremental splitting of probability density functions

The research described in this paper focuses on possibilities of avoiding the tedious training of hidden-Markov-models when setting up a new recognition task. A major speaker independent cause of the reduction of recognition accuracy is a mismatch of the phonetic contexts between the training and testing data. To overcome this problem, we introduced in previous work the idea of an update of task independent acoustic models by means of Bayesian learning. In this paper we introduce a new approach of adaptively splitting the probability density functions (PDFs) of a continuous density HMM. The goal is to model the appropriate state PDFs better so that they can more accurately match new contexts that are observed while the system is in service. Splitting and Bayesian adaptation yields a remarkable reduction of word error rate compared to Bayesian adaptation only