US 12,266,341 B1
Sending media comments using a natural language interface
Shubhendra Agrawal, Seattle, WA (US); Nikhila Bhat, Issaquah, WA (US); Saurabh Rajnath Chaurasia, Kirkland, WA (US); Saurav Kachhwaha, Bellevue, WA (US); Yeqing Wang, Bellevue, WA (US); Supraj Kolluri, Bothell, WA (US); Abhinaw Dixit, Redmond, WA (US); Prateek Ramesh Chandra Shah, Issaquah, WA (US); Michelle Susan Gaseor, Seattle, WA (US); Edward Hein-Ho Tsang, Seattle, WA (US); and Aaron Lamar Wilson, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Dec. 15, 2022, as Appl. No. 18/081,926.
Int. Cl. G10L 13/027 (2013.01); G06F 3/16 (2006.01); G10L 15/18 (2013.01)
CPC G10L 13/027 (2013.01) [G06F 3/167 (2013.01); G10L 15/1815 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a user device, first audio data;
performing speech processing using the first audio data to determine first intent data representing a request to receive first media content;
sending, to a first system component corresponding to the first media content, first data representing a request to send the first media content to the user device;
receiving, from the user device, a first identifier corresponding to the first media content;
sending, to a context storage, the first identifier;
receiving, from the user device, second audio data;
performing speech processing using the second audio data to determine second intent data representing a request to send a media comment;
in response to determining the second intent data, sending, to a second system component, second data representing a request to receive the media comment from the user device;
determining, using the first identifier, to send the media comment to a third system component associated with a creator of the first media content;
causing, by the second system component, the user device to output first synthesized speech representing a first indication to begin recording the media comment;
receiving, from the user device, third audio data representing the media comment;
receiving a second indication to send the media comment; and
sending, to the third system component based on the second indication, a notification that a new media comment is available.