Speech dialogue control method

• US 9,472,193 B2
• Filed: 05/01/2015
• Issued: 10/18/2016
• Est. Priority Date: 09/03/2013
• Status: Expired due to Fees

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Inventors: Nishikawa, Yuri, Yamagami, Katsuyoshi
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US14/702,259
• Publication Number:
  US 20150235642A1
• Time in Patent Office: 536 Days
• Field of Search: 704246-252
• US Class Current: 1/1
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: H04N 1/00403 Voice input means, e.g. voice commands

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.

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 to the speech dialogue system, from the voice input device;

extracting first voice information, indicating first voiceprint data of a first user who has input the first instruction information, contained in the received first instruction information, and recognizing the first instruction in order to identify processing to be executed;

requesting the first user to input complementary information of the first instruction information to uniquely identify the processing, when it is determined that the first instruction information is not complete enough to uniquely identify the processing;

extracting, from utterance information which is voice uttered by a second user that has been received from the voice input device after the requesting, second voice information indicating second voiceprint data of the second user who has input this utterance information;

determining whether or not the first voice information and the second voice information that have been extracted match to determine whether or not the first user is identical to the second user; and

when 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, the first voice information and the second voice information that have been input.

2. The speech dialogue control method according to claim 1,

wherein, when second instruction information indicating a second instruction to uniquely identify the processing has been received from the voice input device as the utterance information, the second instruction which the second instruction information represents is recognized, processing to be executed is uniquely identified based on the recognition result of the first instruction and the second instruction, the second voice information indicating the second voiceprint of the second user who has input the second instruction information is extracted from the second instruction information, and whether or not the first voice information and the second voice information match is determined.

3. The speech dialogue control method according to claim 2,

wherein, when determination is made that the first voice information and the second voice information match, the identified processing is executed.

4. The speech dialogue control method according to claim 1,

wherein, when the first voice information and the second voice information match, a speech content which the received utterance information represents is recognized, it is determined that the processing to be executed is uniquely identified based on the first instruction and the recognition results of the speech content, and the identified processing is executed.

5. The speech dialogue control method according to claim 4,

wherein the identified processing is search processing to search for any information.

6. The speech dialogue control method according to claim 4,

wherein the speech dialogue system is further connected to an electric appliance,

and wherein the identified processing is control processing to control operations of the electric appliance.

7. The speech dialogue control method according to claim 4,

wherein, in a case where execution of the identified processing has ended, the speech dialogue between the first user and the speech dialogue system is ended, and a speech reception state of the speech dialogue system is set to neutral.

8. The speech dialogue control method according to claim 1,

wherein the extracted first voice information is stored in memory,

and wherein the first voice information is read out from the memory, and whether or not the first voice information and the second voice information match is determined.

9. The speech dialogue control method according to claim 1,

wherein, when a predetermined amount of time elapses after the requesting, the speech dialogue between the first user and the speech dialogue system is ended, and a speech reception state of the speech dialogue system is set to neutral.

10. The speech dialogue control method according to claim 1,

wherein the voice input device and the speech dialogue system are connected by a network,

and wherein, in a case of detecting that connection by the network has been cut off after the requesting, the speech dialogue between the first user and the speech dialogue system is ended, and a speech reception state of the speech dialogue system is set to neutral.

11. The speech dialogue control method according to claim 1,

wherein the voice input device and the speech dialogue system are connected by a network,

and wherein, in a case of detecting that connection by the network has been cut off after the requesting, the speech dialogue between the first user and the speech dialogue system is ended, and the first user is notified that the network has been cut off.

12. The speech dialogue control method according to claim 11,

wherein notification to the first user that the network has been cut off is performed by outputting voice indicating the cutoff.

13. The speech dialogue control method according to claim 11,

wherein notification to the first user that the network has been cut off is performed by outputting an image indicating the cutoff.