	US 11,854,549 B2
	Systems and methods for distinguishing valid voice commands from false voice commands in an interactive media guidance application
Edison Lin, Los Altos Hills, CA (US); Rowena Young, Menlo Park, CA (US); and Lauren Palmateer, San Francisco, CA (US)
Assigned to Rovi Guides, Inc., San Jose, CA (US)
Filed by Rovi Guides, Inc., San Jose, CA (US)
Filed on Dec. 14, 2022, as Appl. No. 18/080,873.
Application 18/080,873 is a continuation of application No. 16/467,733, granted, now 11,557,290, previously published as PCT/US2016/067499, filed on Dec. 19, 2016.
Prior Publication US 2023/0223020 A1, Jul. 13, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/02 (2006.01); G10L 15/20 (2006.01); G10L 15/22 (2006.01); G10L 21/0316 (2013.01); H04R 1/32 (2006.01)

CPC G10L 15/22 (2013.01) [G10L 21/0316 (2013.01); H04R 1/326 (2013.01); G10L 2015/223 (2013.01)]

20 Claims

1. A method for distinguishing valid voice commands from false voice commands in an interactive media guidance application, comprising:

receiving, via a first unidirectional microphone of a user device, a first input including a signature sound sequence at a first time, wherein the signature sound sequence has a frequency outside audible frequency for humans;

receiving, via a second unidirectional microphone of the user device, a second input including the signature sound sequence at the first time;

determining a first reference gain based on an average of a first gain of the first input and a second gain of the second input;

normalizing the first gain based on the first reference gain;

normalizing the second gain based on the first reference gain;

determining a metric for a current location of the user device based on a difference between the normalized first gain and the normalized second gain;

receiving, at the user device, a voice command;

determining, using the control circuitry, based on the voice command, a gain for the voice command;

determining whether the gain for the voice command is different from the metric; and

in response to determining that the gain for the voice command is different from the metric, executing the voice command.

11. A system for distinguishing valid voice commands from false voice commands in an interactive media guidance application, comprising:

communications circuitry configured to:

receive, via a first unidirectional microphone, a first input including a signature sound sequence at a first time, wherein the signature sound sequence has a frequency outside audible frequency for humans;

receive, via a second unidirectional microphone, a second input including the signature sound sequence at the first time;

receive a voice command; and

control circuitry configured to:

determine a first reference gain based on an average of a first gain of the first input and a second gain of the second input;

normalize the first gain based on the first reference gain;

normalize the second gain based on the first reference gain;

determine a metric based on a difference between the normalized first gain and the normalized second gain;

determine, using the control circuitry, based on the voice command, a gain for the voice command;

determine whether the gain for the voice command is different from the metric; and

in response to determining that the gain for the voice command is different from the metric, execute the voice command.