This paper summarizes the work of the "Rapid Speech Recognizer Adaptation" team in the workshop held at Johns Hopkins University in the summer of 1998. The project addressed the modeling of dependencies between units of speech with the goal of making more effective use of small amounts of data for speaker adaptation. A variety of statistical dependence models were investigated, including (i) a Gaussian multiscale process governed by a stochastic linear dynamical system on a tree, (ii) a simple hierarchical tree-structured prior, (iii) explicit correlation models and (iv) Markov Random elds. In particular, we investigated dependence models of the bias components of "cascade" transforms of the Gaussian means, which improved the accuracy of the widely used adaptation by transform (constrained re-estimation). Modeling methodologies are contrasted, and comparative performance on the Switchboard task is presented under identical test conditions for supervised and unsupervised adaptation with controlled amounts of adaptation speech.

This paper summarizes the work of the “Rapid Speech Recognizer Adaptation ” team in the workshop held at Johns Hopkins University in the summer of 1998. The project addressed the modeling of dependencies between units of speech with the goal of making more effective use of small amounts of data for speaker adaptation. A variety of methods were investigated and their effectiveness in a rapid adaptation task defined on the SWITCHBOARD conversational speech corpus is reported. 1.