US 11,990,120 B2
Non-speech input to speech processing system
Travis Grizzel, Snoqualmie, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 16, 2020, as Appl. No. 16/902,992.
Application 16/902,992 is a continuation of application No. 15/389,742, filed on Dec. 23, 2016, granted, now 10,692,485.
Prior Publication US 2021/0035552 A1, Feb. 4, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/01 (2013.01); G06F 3/01 (2006.01); G10L 13/00 (2006.01); G10L 15/18 (2013.01); G10L 15/187 (2013.01); G10L 15/24 (2013.01); G10L 15/08 (2006.01)
CPC G10L 15/01 (2013.01) [G06F 3/017 (2013.01); G10L 13/00 (2013.01); G10L 15/18 (2013.01); G10L 15/187 (2013.01); G10L 15/24 (2013.01); G10L 2015/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A device comprising:
at least one motion sensor;
at least one microphone;
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the device to:
receive, from the at least one motion sensor, motion data corresponding to motion of the device, wherein the device is attached to a body part;
determine, based at least in part on processing by a model, that the motion of the device about a first axis corresponds to the motion of the body part about the first axis;
determine the motion data corresponds to a wake gesture;
determine input audio data based at least on an utterance captured by the at least one microphone;
determine the wake gesture is associated with a command to perform speech processing; and
based at least in part on association between the wake gesture and the command, send the input audio data to at least one speech processing component.