US 12,073,827 B2
Pre-emptively limiting responsiveness of various assistant devices in an environment using an inaudible tone or other rendered output
Vikram Aggarwal, Palo Alto, CA (US); and Moises Morgenstern Gali, San Francisco, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/251,479
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Feb. 26, 2020, PCT No. PCT/US2020/019845
§ 371(c)(1), (2) Date Dec. 11, 2020,
PCT Pub. No. WO2021/173127, PCT Pub. Date Sep. 2, 2021.
Prior Publication US 2021/0335348 A1, Oct. 28, 2021
Int. Cl. G10L 15/18 (2013.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 25/78 (2013.01)
CPC G10L 15/1815 (2013.01) [G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 25/78 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
causing, by a first computing device and independent of any detection of invocation phrase by the first computing device, the first computing device to render a particular audio output via one or more speakers coupled to the first computing device,
wherein the particular audio output is inaudible to a human but is audibly detectable by one or more microphones of a second computing device located in an environment with the first computing device, and
wherein, responsive to the particular audio output being detected at the second computing device by the one or more microphones, the second computing device at least temporarily limits performance of certain processing of audio data, including spoken input, from one or more users, that is detected at the second computing device;
subsequent to causing the first computing device to render the particular audio output, and while the second computing device is limiting performance of the certain processing of audio data, including the spoken input:
determining, by the first computing device, that a user has provided a spoken utterance to an automated assistant that is accessible via the first computing device,
wherein the spoken utterance corresponds to a request for the automated assistant to perform one or more actions; and
causing, by the first computing device and in response to the spoken utterance, the automated assistant to initialize performance of the one or more actions,
wherein, based on temporarily limiting performance of the certain processing of audio data, including the spoken input, the second computing device does not initialize performance of the one or more actions in response to the spoken utterance.