Domain Adaptation Augmente in Spoken Dialog

In the development of spoken dialog systems, domain adaptation and dialog state-dependent language model are usually researched separately. This paper proposes a new approach for domain adaptation augmented by the dialog state-dependence, which means a dialog turn based cache model decaying synchronously with the dialog state change. Through this approach it’s more simple and rapid to adapt a Chinese spoken dialog system to a new task. Two different tasks, the train ticket reservation and the park guide are selected respectively as the target task in the experiments. The consistent reductions of perplexity and character error rate are observed during the adaptation.