US 12,249,331 B2
Multi-layer keyword detection
Christopher Wayne Lockhart, Louisville, KY (US); Matthew Joseph Cole, Arlington, MA (US); and Xulei Liu, Brighton, MA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 8, 2023, as Appl. No. 18/144,465.
Application 18/144,465 is a continuation of application No. 17/590,406, filed on Feb. 1, 2022, granted, now 11,646,027.
Application 17/590,406 is a continuation of application No. 16/783,826, filed on Feb. 6, 2020, granted, now 11,250,851, issued on Feb. 15, 2022.
Application 16/783,826 is a continuation of application No. 16/131,705, filed on Sep. 14, 2018, granted, now 10,679,625, issued on Jun. 9, 2020.
Application 16/131,705 is a continuation of application No. 15/370,216, filed on Dec. 6, 2016, granted, now 10,079,015, issued on Sep. 18, 2018.
Prior Publication US 2023/0360647 A1, Nov. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/02 (2006.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 15/30 (2013.01); G10L 15/32 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 15/02 (2013.01); G10L 15/08 (2013.01); G10L 15/26 (2013.01); G10L 2015/025 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01); G10L 15/30 (2013.01); G10L 15/32 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining first audio data corresponding to audio to be output;
processing the first audio data to detect a keyword;
after determining the first audio data includes the keyword, entering a second operation mode of a first device to disregard the keyword; and
after entering the second operation mode of the first device, causing the audio to be output.