METHOD FOR REALIZING A TELEPHONE INFORMATION RETRIEVAL SERVICE WITH MULTIPLY ENTERED SPEECH INPUTS USING SPEECH RECOGNITION TECHNOLOGY

摘要

1. the art that the invention defined in the claims; The present invention will on a computer-readable recording medium recording a program for realizing a method and multi-step speech recognition him telephone information service.; 2. The invention attempts to solve the technical challenges; How the present invention, multi-stage speech recognition of the telephone information service voice recognition in addition to a speech recognition function to the telephone information service for processing the multi-level input in the system for providing a user desired information in the minimum time with minimum user effort and user input and also to provide a computer readable recording medium recording a program for realizing him.; 3. Resolution of the subject matter of the invention,; The present invention, the multi-level input at the time of the telephone information service in order to process the speech recognition, to match the timing for receiving the information current when the recognition result is output in the recognition step and the input of the next recognition step requires, at the time of a first step of converting the previous step at the time of the error of the recognition resu A second step during the multi-step input processed, preserved the group information entered in the database so as not to re-enter the user-input information group; And a third step of the service a call information the user desires to take to re-enter the information from the user switches the recognition steps for the group desired user changes of the input information stored in the database in step the user wants to modify the including.; 4. An important use of the invention,; The invention yiyongdoem like speech recognition train information service.