CPC G10L 15/22 (2013.01) [G06F 16/3343 (2019.01); G10L 15/02 (2013.01); G10L 2015/025 (2013.01); G10L 2015/223 (2013.01)] | 20 Claims |
1. A method comprising:
identifying a plurality of content items available for consumption, wherein the identification is based on a search performed by a server based at least in part on a user profile associated with a user interface correlated to a content platform;
retrieving metadata for each of the plurality of content items;
generating, based on a plurality of voice command templates, one or more candidate voice commands, wherein each candidate voice command comprises a verb and metadata corresponding to a content item of the plurality of content items;
generating, for each candidate voice command, a respective recall score based at least in part on a number of matching phonetic features in a respective candidate voice command;
selecting a candidate voice command based on recall scores of the one or more candidate voice commands; and
generating for output the selected candidate voice command on the user interface of a computing device that is correlated to the content platform.
|