US Patent Issued to NETFLIX on Sept. 2 for "Techniques for training a multitask learning model to assess perceived audio quality" (California Inventors)

ALEXANDRIA, Va., Sept. 3 -- United States Patent no. 12,406,686, issued on Sept. 2, was assigned to NETFLIX INC. (Los Gatos, Calif.).

"Techniques for training a multitask learning model to assess perceived audio quality" was invented by Chih-Wei Wu (Los Gatos, Calif.), Phillip A. Williams (Los Gatos, Calif.) and William Francis Wolcott IV (Los Gatos, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various embodiments, a training application trains a multitask learning model to assess perceived audio quality. The training application computes a set of pseudo labels based on a first audio clip and multiple models. The set of pseudo labels specifies metric values for a set of metrics that are relevant ...