US 12,293,762 B2
Multi-mode guard for voice commands
Michael J. LeBeau, New York, NY (US); and Mat Balez, San Francisco, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Dec. 16, 2022, as Appl. No. 18/083,315.
Application 18/083,315 is a continuation of application No. 17/109,265, filed on Dec. 2, 2020, abandoned.
Application 17/109,265 is a continuation of application No. 16/216,516, filed on Dec. 11, 2018, granted, now 10,891,953, issued on Jan. 12, 2021.
Application 16/216,516 is a continuation of application No. 15/371,027, filed on Dec. 6, 2016, granted, now 10,181,324, issued on Jan. 15, 2019.
Application 15/371,027 is a continuation of application No. 13/859,588, filed on Apr. 9, 2013, granted, now 9,530,410, issued on Dec. 27, 2016.
Prior Publication US 2023/0120601 A1, Apr. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G10L 15/08 (2006.01)
CPC G10L 15/22 (2013.01) [G10L 2015/088 (2013.01); G10L 2015/223 (2013.01); G10L 2015/228 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors associated with a head mounted display, the method comprising:
transitioning the head mounted display into a second interface mode from a first interface mode in response to receiving a spoken utterance from a user captured by at least one sensor of the head mounted display,
wherein the first interface mode has a first set of supported spoken commands and the second interface mode has a second set of supported spoken commands, the first set of supported spoken commands different than the second set of supported spoken commands;
wherein the second interface mode is operable to process the second set of supported spoken commands specific to the second interface mode;
enabling, in response to transitioning the head mounted display into the second interface mode, the second set of supported spoken commands that are specific to the second interface mode,
wherein the second interface mode corresponds to a current state of a user interface of the head mounted display; and
wherein the second interface mode and the first interface mode are each one of multiple interface modes each corresponding to alternate states of the user interface of the head mounted display, each of the multiple interface modes having a different set of supported spoken commands;
while the head mounted display is in the second interface mode, and responsive to enabling the second set of supported spoken commands;
receiving audio data captured by at least one audio sensor of the head mounted display;
analyzing the audio data to determine whether any of the second set of supported spoken commands that are specific to the second interface mode, are included in the audio data;
determining whether the audio data contains a given spoken command, of the second set of supported spoken commands and that the audio data is received within a threshold period of time; and
causing, in response to determining the audio data being received within the threshold period of time contains the given spoken command, performance of one or more actions, via the head mounted display, that correspond to the given spoken command.