ALEXANDRIA, Va., June 17 -- United States Patent no. 12,315,508, issued on May 27, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Selectively activating on-device speech recognition, and using recognized text in selectively activating on-device NLU and/or on-device fulfillment" was invented by Michael Golikov (Merlischachen, Switzerland), Zaheed Sabur (Baar, Switzerland), Denis Burakov (Zurich), Behshad Behzadi (Freienbach, Switzerland), Sergey Nazarov (Zurich), Daniel Cotting (Islisberg, Switzerland), Mario Bertschler (Zurich), Lucas Mirelmann (Zurich), Steve Cheng (Los Altos, Calif.), Bohdan Vlasyuk (Zurich), Jonathan Lee (Brooklyn, N.Y.), Lucia Terrenghi (Zurich) and Adrian Zumbrunnen (Zurich).

According to the abstract* released...