DIALOG SYSTEM WITH AUTOMATIC REACTIVATION OF SPEECH ACQUIRING MODE

• US 20170110129A1
• Filed: 12/30/2016
• Published: 04/20/2017
• Est. Priority Date: 11/28/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gelfenbeyn, Ilya Gennadyevich, Goncharuk, Artem, Sirotin, Pavel Aleksandrovich
• Granted Patent: US 10,102,854 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/083 Recognition networks G10L15/142, G10L15/16 take precedence
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

Embodiments of the disclosure generally relate to a dialog system allowing for automatically reactivating a speech acquiring mode after the dialog system delivers a response to a user request. The reactivation parameters, such as a delay, depend on a number of predetermined factors and conversation scenarios. The embodiments further provide for a method of operating of the dialog system. An exemplary method comprises the steps of: activating a speech acquiring mode, receiving a first input of a user, deactivating the speech acquiring mode, obtaining a first response associated with the first input, delivering the first response to the user, determining that a conversation mode is activated, and, based on the determination, automatically re-activating the speech acquiring mode within a first predetermined time period after delivery of the first response to the user.

Claims

1. A method for operating of a dialog system, the method comprising:

activating, by means of a computing device comprising one or more processors and a memory, a speech acquiring mode;

receiving, by means of the computing device, a first input of a user;

deactivating, by means of the computing device, the speech acquiring mode;

obtaining, by means of the computing device, a first response associated with the first input;

delivering, by means of the computing device, the first response to the user;

determining, by means of the computing device, that a conversation mode is activated;

selecting, by means of the computing device, a first predetermined time period based on a conversational length of the first response; and

based on the determination that the conversation mode is activated, automatically re-activating, by means of the computing device, the speech acquiring mode within the first predetermined time period after delivery of the first response to the user.

2. The method of claim 1, wherein the first input of the user comprises a speech-based input.

3. The method of claim 1, wherein the first input of the user comprises a text-based input.

4. The method of claim 1, further comprising:

receiving, by means of the computing device, a second input of the user;

obtaining, by means of the computing device, a second response associated with the second input; and

delivering, by means of the computing device, the second response to the user.

5. The method of claim 4, further comprising deactivating, by means of the computing device, the speech acquiring mode after receiving of the second input of the user.

6. The method of claim 1, further comprising:

determining, by means of the computing device, that a voice activation mode is activated; and

based on the determination that that the voice activation mode is activated, providing, by means of the computing device, an audio message associated with the first response to the user.

7. The method of claim 1, further comprising:

determining, by means of the computing device, that a voice activation mode is deactivated; and

based on the determination that that the voice activation mode is deactivated, displaying, by means of the computing device, a message associated with the first response to the user.

8. The method of claim 1, wherein the conversation mode enables the computing device to record the first input of the user.

9. The method of claim 1, wherein the conversation mode enables the computing device to recognize the first input of the user.

10. The method of claim 1, wherein the conversation mode enables the computing device to transmit the first input of the user to a remote server.

11. The method of claim 1, further comprising:

recognizing, by means of the computing device, the first input of the user to generate a first recognized input;

generating, by means of the computing device, the first response to the recognized input.

12. The method of claim 1, further comprising selecting, by means of the computing device, the first predetermined time period is further based on a type of the first response, wherein the type of the first response depends on a text provided in the first response.

13. The method of claim 1, wherein the conversational length of the first response is a number of letters contained in the first response.

14. The method of claim 1, wherein the first predetermined time period is between 1 second and 10 seconds.

15. The method of claim 1, further comprising:

setting, by the computing device, an automatic recognition flag to the first response based on a type of the first response or a type of the first input; and

suppressing, by the computing device, the speech acquiring mode based on the automatic recognition flag.

16. The method of claim 1, wherein the first response comprises metadata, wherein the metadata sets the first predetermined time period.

17. The method of claim 1, wherein the speech acquiring mode is re-activated for a second predetermined time period.

18. The method of claim 17, wherein the first response comprises metadata and wherein the metadata includes instructions to cause the dialog system to set the second predetermined time period based on the metadata.

19. A dialog system, the system comprising:

a speech recognition module configured to receive a first user input and recognize at least a part of the first user input and generate a first recognized input, when the speech recognition module is in a speech acquiring mode;

a dialog manager configured to activate and deactivate the speech acquiring mode, and to generate a first response to the first recognized input;

a user output module configured to deliver the first response to a user; and

wherein the dialog manager is further configured to select a first predetermined time period based on a conversational length of the first response and automatically re-activate the speech acquiring mode within the first predetermined time period after delivering of the first response to the user, when a conversation mode is activated.

20. A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more processors, cause the one or more processors to implement a method for operating of a dialog system, the method comprising:

activating a speech acquiring mode;

receiving a first input of a user;

deactivating the speech acquiring mode;

obtaining a first response associated with the first input;

delivering the first response to the user;

determining that a conversation mode is activated;

selecting a first predetermined time period based on a conversational length of the first response; and

based on the determination that the conversation mode is activated, automatically re-activating the speech acquiring mode within the first predetermined time period after delivering of the first response to the user.