Towards Domain { Independentunderstanding of Spontaneous Speechr

We rst describe EVAR, a state{of{the{art speech understanding and dialog system which application domain is train time table information retrieval. The system | as others | is devided into two main components: a speech recognizer based on hidden Markov models (a statistical approach) and a knowledge-based linguistic component developed in a semantic network environment. When switching to a new domain the knowledge{base would have to be changed manually, which means a great eeort. Thus, we favor for a statistical approach for linguistic analysis. This would only mean retraining the models on annotated corpora from the new domain. A promising approach are semantic classiication trees. Since the speech recognizer already relies on statistical models only (part of) its parameters have to be retrained when switching to a new domain.