US 11,972,095 B2
Voice assistant-enabled client application with user view context and multi-modal input support
Tudor Buzasu Klein, Yokohama (JP); Viktoriya Taranov, Kirkland, WA (US); Sergiy Gavrylenko, Issaquah, WA (US); Jaclyn Carley Knapp, Redmond, WA (US); Andrew Paul McGovern, Redmond, WA (US); Harris Syed, Redmond, WA (US); Chad Steven Estes, Redmond, WA (US); Jesse Daniel Eskes Rusak, Redmond, WA (US); David Ernesto Heekin Burkett, Redmond, WA (US); Allison Anne O'Mahony, Redmond, WA (US); Ashok Kuppusamy, Redmond, WA (US); Jonathan Reed Harris, Redmond, WA (US); Jose Miguel Rady Allende, Redmond, WA (US); Diego Hernan Carlomagno, Redmond, WA (US); Talon Edward Ireland, Redmond, WA (US); Michael Francis Palermiti, II, Redmond, WA (US); Richard Leigh Mains, Redmond, WA (US); and Jayant Krishnamurthy, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed on Oct. 22, 2021, as Appl. No. 17/508,762.
Application 17/508,762 is a continuation in part of application No. 17/364,362, filed on Jun. 30, 2021, granted, now 11,789,696.
Claims priority of provisional application 63/165,037, filed on Mar. 23, 2021.
Prior Publication US 2022/0308718 A1, Sep. 29, 2022
Int. Cl. G06F 3/0484 (2022.01); G06F 3/16 (2006.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01)
CPC G06F 3/0484 (2013.01) [G06F 3/167 (2013.01); G10L 15/08 (2013.01); G10L 15/22 (2013.01); G10L 2015/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving utterance data via a client application, the utterance data being associated with a voice utterance of a user;
receiving an indication that the user has engaged in manual user input at a user interface of the client application, the manual user input corresponding to a request to perform a task at the user interface of the client application;
in response to the receiving of the indication that the user has engaged in the manual user input at the user interface of the client application, causing a deactivation of a microphone such that: the microphone refrains from capturing audio data, or that the audio data received via the microphone is not processed;
based at least in part on the deactivation of the microphone, causing the client application to respond to the manual user input by performing the task at the user interface and refraining from responding to the voice utterance.