SPEECH DIALOGUE CONTROL METHOD
First Claim
1. A speech dialogue control method of a speech dialogue system where connection is made to a voice input device that inputs user voice, the method comprising:
- receiving first instruction information, representing a first instruction content as to the speech dialogue system, from the voice input device;
extracting first voice information, indicating a voice feature value of the user who has input the first instruction information, contained in the received first instruction information, and recognizing a first instruction content which the first instruction information represents;
performing instruction request notification, in a case where the recognition result of the first instruction content is that processing to be executed could not be uniquely identified based on the first instruction content, thereby prompting the user to input information necessary for uniquely identifying the processing;
extracting, from utterance information which is voice uttered by the user that has been received from the voice input device after the instruction request notification, second voice information indicating a voice feature value of the user who has input this utterance information, and determining whether or not the first voice information and the second voice information that have been extracted match; and
in a case where determination is made that the first voice information and the second voice information do not match, executing processing to make notification to the effect that input of the utterance information cannot be accepted, or not executing processing identified based on the first instruction content and the voice information that have been input.
2 Assignments
0 Petitions
Accused Products
Abstract
A cloud server extracts voiceprint data from voice data of a user, and distinguishes the user. The cloud server identifies a task which the user instructs, from the voice data of the user. If contexts required to execute the task have not been amassed, the cloud server registers the distinguished user as a task owner, and notifies the user with a reply sentence to cause the user to speak the required context. If the voiceprint data of the voice data which the user has uttered matches the voiceprint data of the user A, and all required contexts are amassed, the cloud server causes a device to execute the task.
35 Citations
13 Claims
-
1. A speech dialogue control method of a speech dialogue system where connection is made to a voice input device that inputs user voice, the method comprising:
-
receiving first instruction information, representing a first instruction content as to the speech dialogue system, from the voice input device; extracting first voice information, indicating a voice feature value of the user who has input the first instruction information, contained in the received first instruction information, and recognizing a first instruction content which the first instruction information represents; performing instruction request notification, in a case where the recognition result of the first instruction content is that processing to be executed could not be uniquely identified based on the first instruction content, thereby prompting the user to input information necessary for uniquely identifying the processing; extracting, from utterance information which is voice uttered by the user that has been received from the voice input device after the instruction request notification, second voice information indicating a voice feature value of the user who has input this utterance information, and determining whether or not the first voice information and the second voice information that have been extracted match; and in a case where determination is made that the first voice information and the second voice information do not match, executing processing to make notification to the effect that input of the utterance information cannot be accepted, or not executing processing identified based on the first instruction content and the voice information that have been input. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
Specification