| 摘要 |
PURPOSE:To improve a recognition performance by fetching only the combination of the related word candidate while using the information being described the relation between words already, in plural recognizing candidates obtained by recognizing an inputted voice. CONSTITUTION:The inputted voice is used as plural recognizing candidates by a voice recognizing part 2, and the word series for retrieving are selected by a word series selecting part 3 out of them. The relation between key words concerning the information retrieved beforehand is described in a concept network table 8. A retrieving processing part 4 prepares the retrieving conditions sentence from a word series for retrieving and a concept network, collates this with a concept relation network, selects the contents to be retrieved is selected and the information is retrieved. Thus, a user can retrieve the information even from the ambiguous memory while the user freely interacts with a system, and the recognition performance can be improved. |
