US Patent Issued to Descript on Sept. 30 for "Training machine learning frameworks to generate studio-quality recordings through manipulation of noisy audio signals" (Canadian, American Inventors)

ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,431,154, issued on Sept. 30, was assigned to Descript Inc. (San Francisco).

"Training machine learning frameworks to generate studio-quality recordings through manipulation of noisy audio signals" was invented by Prem S. Seetharaman (Sacramento, Calif.) and Kundan Kumar (Montreal).

According to the abstract* released by the U.S. Patent & Trademark Office: "Introduced here are computer programs and associated computer-implemented techniques for manipulating noisy audio signals to produce clean audio signals that are sufficiently high quality so as to be largely, if not entirely, indistinguishable from "rich" recordings generated by recording studios. When a noisy audio signal is obta...