Systems and methods for selectively activating and interacting with a speech recognition service during application runtime without interrupting execution of the application

Patent metadata

Field	Value
Publication number	US-10937425-B2
Application number	US-201916244818-A
Country	US
Kind code	B2
Filing date	Jan 10, 2019
Priority date	Jan 10, 2019
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

Systems and methods are provided that may be implemented to allow an information handling system user to selectively activate and interact with a speech recognition service for system control during application runtime on the same system, and without interrupting the separate application on the same information handling system. The activated speech recognition service may respond to verbal commands to control one or more operating characteristics of the information handling system while the separate application (e.g., such as a computer game) is simultaneously executing without interruption on the same system. A user may be allowed to activate the speech recognition service using one or more different activation modes, e.g., using eye tracking, call word recognition, and/or hardware input/output actuation.

First claim

What is claimed is:

1. A method, comprising:
executing an application on a first information handling system to display a graphics scene to a human user of the first information handling system on a display device;
receiving analog audio sounds from the human user of the first information handling system that is viewing the displayed graphics scene, and transferring the received audio sounds from the first information handling system as outgoing voice chat to one or more other information handling systems communicatively coupled by a network to the first information handling system;
detecting an activation action from the human user of the first information handling system while the voice chat is unmuted and while the graphics scene is displayed on the display device; and
selectively activating at least one deactivated separate service on the first information handling system that is different from the executing application to respond to the detected activation action without interrupting the executing application, the response by the separate service to the detected activation action comprising:
temporarily muting the outgoing voice chat and using speech recognition while the outgoing voice chat is muted to receive and analyze any analog audio signals received from the human user of the first information handling system while the outgoing voice chat is muted to recognize a predefined voice command spoken by the human user of the first information handling system while the outgoing voice chat is muted,
then, while the outgoing voice chat remains muted, executing a command corresponding to the predefined voice command to take at least one predefined response action while the outgoing voice chat remains muted to modify one or more operating characteristics of the executing application and/or other components of the information handling system, and
then unmuting the outgoing voice chat and deactivating the separate service after and in response to executing the command.

2. The method of claim 1 , where the response by the separate service to the detected activation action further comprises temporarily muting the outgoing voice chat while using speech recognition while the outgoing voice chat is muted to receive and analyze any analog audio signals received from the human user of the first information handling system while the outgoing voice chat is muted to recognize a predefined voice command spoken by the human user of the first information handling system for a predetermined maximum threshold value of elapsed listening time that begins when the activation action is first detected; and then unmuting the outgoing voice chat and deactivating the separate service after expiration of the predetermined maximum threshold value of elapsed listening time if no analog audio signals are received before the expiration of the predetermined maximum threshold value of elapsed listening time that are recognized as a predefined voice command spoken by the human user of the first information handling system.

3. The method of claim 2 , further comprising only using the speech recognition while the outgoing voice chat is muted during the predetermined maximum threshold value of elapsed listening time to receive and analyze any analog audio signals received from the human user of the first information handling system while the outgoing voice chat is muted to recognize a predefined voice command spoken by the human user of the first information handling system.

4. The method of claim 1 , where the detected activation action from the human user of the first information handling system comprises detection of a tracked gaze of the human user of the first information handling system upon a predetermined activation area.

5. The method of claim 1 , where the detected activation action from the human user of the first information handling system comprises detection of a predetermined call word or activation phrase spoken by the human user of the first information handling system.

6. The method of claim 1 , where the detected activation action from the human user of the first information handling system comprises detection of the actuation of a predetermined hardware (input/output) I/O of the first information handling system by the human user of the first information handling system.

7. The method of claim 1 , further comprising responding to the detected activation action by temporarily displaying a user interface (UI) over at least a portion of the graphics scene on the display device while muting the outgoing voice chat and using speech recognition to receive and analyze any analog audio signals received from the human user of the first information handling system while the outgoing voice chat is muted to recognize a predefined voice command spoken by the human user of the first information handling system; and then ceasing display of the UI over the at least a portion of the graphics scene on the display device when unmuting the outgoing voice chat.

8. The method of claim 1 , further comprising responding to the detected activation action by:
temporarily muting the outgoing voice chat and using speech recognition while the outgoing voice chat is muted for a predetermined maximum threshold value of elapsed listening time to listen for and analyze any analog audio signals received from the human user of the first information handling system while the outgoing voice chat is muted to recognize a predefined voice command spoken by the human user of the first information handling system while the outgoing voice chat is muted,
then executing a command corresponding to any predefined voice command received before expiration of the predetermined maximum threshold value of elapsed listening time to take the at least one predefined response action while the outgoing voice chat remains muted to modify the one or more operating characteristics of the executing application and/or other components of the information handling system, and
then unmuting the outgoing voice chat upon occurrence of either the expiration of the predetermined maximum value of elapsed listening time threshold or after and in response to the execution of the command corresponding to a predefined voice command to take the at least one predefined response action to modify the one or more operating characteristics of the executing application and/or other components of the information handling system.

9. The method of claim 1 , where the at least one response action comprises at least one of opening a new application on the first information handling system, closing an existing application on the first information handling system, sending a text message or in-application message from the first information handling system to a user of another information handling system, recording a video on the first information handling system or taking a screenshot of the displayed graphics scene on the first information handling system, uploading or posting a video or screenshot of the displayed graphics scene across the network from the first information handling system to a server, changing a selected keyboard lighting theme on the first information handling system, changing keyboard haptics settings on the first information handling system, or changing a selected keyboard macro on the first information handling system.

10. A method, comprising:
executing an application on a first information handling system to display a graphics scene to a human user of the first information handling system on a display device;
tracking a gaze of the human user of the first information handling system that is viewing the displayed graphics scene;
detecting a location of the tracked gaze of the human user of the first i

Assignees

• Dell Products Lp

Inventors

• Summa Erik P
• Pruitt John S
• Baluch Gregory J
• Jackson Simon W

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• A63F13/87

  Communicating with other players during game play, e.g. by e-mail or chat · CPC title

• H04L51/046

  Interoperability with other network applications or services · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title