In this letter, we propose a grammatical structure of the finite state network (FSN) for the recognition of Korean price sentences. It is implemented by arranging the nodes and the arcs of the FSN. Two kinds of grammatical structure are presented. Both are designed according to the grammar constraints of Korean price sentences. The grammar constraints of Korean price sentences are similar to those of English price sentences; the unit is placed after the digit; several digits form a basic group; the basic group appears recursively followed by meta-units, etc. Speaker-independent recognition experiments were conducted, and the results of the FSN's with proposed grammatical structures were compared with those of the FSN without grammatical structure.

This paper describes the linguistic procedure of our speech dialogue system. The procedure is composed of two processes, syntactic analysis using a finite state network, and discourse analysis using a plan recognition model. The finite state network is compiled from regular grammar. The regular grammar is described in order to accept sentences with various styles, for example ellipsis and inversion. The regular grammar is automatically generated from the skeleton of the grammar. The discourse analysis module understands the utterance, generates the next question for users and also predicts words which will be in the next utterance. For an extension number guidance task, we obtained correct recognition results for 93% of input sentences without word prediction and for 98% if prediction results include proper words.