US 12,142,300 B2
Content system with event identification and audio-based editing feature
Michael Cutter, Golden, CO (US); Sunil Ramesh, Cupertino, CA (US); and Karina Levitian, Austin, TX (US)
Assigned to Roku, Inc., San Jose, CA (US)
Filed by Roku, Inc., San Jose, CA (US)
Filed on Nov. 1, 2022, as Appl. No. 18/051,568.
Prior Publication US 2024/0144978 A1, May 2, 2024
Int. Cl. G11B 27/036 (2006.01); G06V 20/40 (2022.01)
CPC G11B 27/036 (2013.01) [G06V 20/44 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by a computing system, video data representing video content;
analyzing, by the computing system, the video data to identify an event that is a subject of the video content, wherein the analyzing comprises:
providing the video data and closed-captioning data associated with the video content to a trained model, wherein the trained model is configured to use at least video data and closed-captioning data as runtime input data to generate event identification data as runtime output data; and
responsive to providing the video data and the closed-captioning data associated with the video data to the trained model, receiving from the trained model, corresponding generated event identification data;
using, by the computing system, the identified event as a basis to select audio content; and
performing, by the computing system, an operation that facilitates editing the video content to include the selected audio content.