Machine Dialog System

We present two concepts for systems with language identication in the context of mul-tilingual information retrieval dialogs. The rst one has an explicit module for language identi cation. It is based on training a common codebook for all the languages and integrating over the output probabilities of language specic n{gram models trained over the codebook sequences. The system can decide for one language either after a prede ned time interval or if the dierence between the probabilities of the languages succeeds a certain threshold. This approach allows to recognize languages that the system can not process and give out a prerecorded message in that language. In the second approach, the trained recognizers of the languages to be recognized, the lexicons, and the language models are combined to one multilingual recognizer. Only allowing transitions between the words from one language, each hypothesized word chain only contains words from one language and language identication is an implicit by-product of the speech recognizer. First results for both language identication approaches are presented.