Automatically altering the audio of an object during video conferences

  • US 10,581,625 B1
  • Filed: 11/20/2018
  • Issued: 03/03/2020
  • Est. Priority Date: 11/20/2018
  • Status: Active Grant
  • ×
    • Pin Icon | RPX Insight
    • Pin
First Claim
Patent Images

1. A method, comprising:

  • obtaining, by a computer device, monitoring data of a user participating in a video conference;

    determining, by the computer device, a level of understanding of the user based on the monitoring data;

    adjusting, by the computer device, an output of the video conference for the user based on the determined level of understanding being less than a threshold;

    determining, by the computer device, a success of the adjusting and updating a learning model based on the determined success;

    using computer vision to segment and identify objects in video of the video conference;

    matching sounds in audio of the video conference to the identified objects; and

    determining one of the identified objects as a focus object of the user,wherein the adjusting the output of the video conference comprises;

    increasing volume of sounds associated with the focus object, and decreasing volume of sounds of other ones of the identified objects.

View all claims

    Thank you for your feedback