US 11,741,981 B2
Voice recognition with timing information for noise cancellation
Ross Gilson, Philadelphia, PA (US); Michael Sallas, Radnor, PA (US); Scott David Kurtz, Mount Laurel, NJ (US); Gary Skrabutenas, Palo Alto, CA (US); and Christopher Stone, Philadelphia, PA (US)
Assigned to Comcast Cable Communications, LLC, Philadelphia, PA (US)
Filed by Comcast Cable Communications, LLC, Philadelphia, PA (US)
Filed on Nov. 11, 2020, as Appl. No. 17/95,228.
Application 17/095,228 is a continuation of application No. 16/257,702, filed on Jan. 25, 2019, granted, now 10,867,615.
Prior Publication US 2021/0312935 A1, Oct. 7, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 21/0216 (2013.01); G10L 21/055 (2013.01); G10L 15/22 (2006.01); G10L 15/20 (2006.01); G10L 21/0208 (2013.01)
CPC G10L 21/0216 (2013.01) [G10L 15/20 (2013.01); G10L 15/22 (2013.01); G10L 21/055 (2013.01); G10L 2015/223 (2013.01); G10L 2021/02082 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a first signal comprising first data indicative of content being rendered by an output device;
receiving, via a user input, a second signal comprising second data;
determining, based on timing information associated with the first signal, a delay associated with receiving the first signal;
synchronizing, based on the determined delay, the second data with the first data;
determining, based on the synchronized first data and second data, whether the second data comprises a component of the content; and
determining, based on filtering the component of the content from the second data, a voice command.