US 11,810,554 B2
Audio message extraction
Neil Christopher Fritz, Tempe, AZ (US); Lakshya Bhagat, Seattle, WA (US); Scott Southwood, Seattle, WA (US); Katelyn Doran, Seattle, WA (US); Brett Lounsbury, Phoenix, AZ (US); and Christo Frank Devaraj, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Reno, NV (US)
Filed by Amazon Technologies, Inc., Reno, NV (US)
Filed on Oct. 9, 2020, as Appl. No. 17/067,315.
Application 17/067,315 is a continuation of application No. 16/431,343, filed on Jun. 4, 2019, granted, now 10,803,856.
Application 16/431,343 is a continuation of application No. 15/392,291, filed on Dec. 28, 2016, granted, now 10,319,375, issued on Jun. 11, 2019.
Prior Publication US 2021/0074275 A1, Mar. 11, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G10L 15/18 (2013.01); G10L 15/30 (2013.01); H04W 4/12 (2009.01); H04M 7/00 (2006.01); G10L 15/22 (2006.01); G06F 40/295 (2020.01); G10L 15/08 (2006.01)
CPC G10L 15/1815 (2013.01) [G06F 40/295 (2020.01); G10L 15/1822 (2013.01); G10L 15/22 (2013.01); G10L 15/30 (2013.01); H04M 7/0042 (2013.01); H04W 4/12 (2013.01); G10L 2015/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving audio input data corresponding to an utterance received by a voice communications device, the audio input data received in response to detection of a wakeword;
determining a messaging intent represented by the audio input data;
determining, based at least in part on the messaging intent, a recipient identifier, the recipient identifier determined with at least a minimum level of confidence;
determining a beginning of a message payload; and
generating audio message data, the audio message data accessible according to the recipient identifier, and the audio message data including the message payload starting from the beginning.