US 11,670,299 B2
Wakeword and acoustic event detection
Ming Sun, Winchester, MA (US); Thibaud Senechai, Somerville, MA (US); Yixin Gao, Cambridge, MA (US); Anish N. Shah, Bedford, MA (US); Spyridon Matsoukas, Hopkinton, MA (US); Chao Wang, Newton, MA (US); and Shiv Naga Prasad Vitaladevuni, Belmont, MA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 17, 2021, as Appl. No. 17/321,999.
Application 17/321,999 is a continuation of application No. 16/452,964, filed on Jun. 26, 2019, granted, now 11,043,218.
Prior Publication US 2021/0358497 A1, Nov. 18, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G10L 15/16 (2006.01)
CPC G10L 15/22 (2013.01) [G10L 15/16 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining a feature vector representing at least one frame of audio data;
determining, using a first model and the feature vector, first output data corresponding to a likelihood that the at least one frame includes a representation of at least part of a word; and
determining, using a second model different from the first model and the feature vector, second output data corresponding to a likelihood that the at least one frame includes a representation of at least part of a non-speech acoustic event, wherein determination of the second output data is performed independently of the first output data.