摘要 |
An interactive speech interface unit of the invention comprises speech recognition means for recognizing input speech of user utterance and converting the recognized input speech into a character string, input statement analysis means for analyzing the character string and converting the analyzed character string into semantic representation, interactive control means for controlling flow of an interactive status and accessing an application, output statement generation means for generating an intermediate language to be outputted to the user, speech generation means for converting the intermediate language into speech and outputting the speech, and application interface means for accessing the application using the semantic representation outputted from the interactive control means, wherein the interactive control means puts series of interactive sequences having calling relations together in a plurality of interactive tasks in association with relations and includes an interactive task hierarchical data base for storing the interactive tasks in a hierarchical structure.
|