US Patent Issued to Google on Sept. 22 for "Using machine learning and discrete tokens to estimate different sound sources from audio mixtures" (American, Swiss, French Inventors)

ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,744,045, issued on Sept. 22, was assigned to Google LLC (Mountain View, Calif.).

"Using machine learning and discrete tokens to estimate different sound sources from audio mixtures" was invented by Hakan Erdogan (Lexington, Mass.), Scott Thomas Wisdom (Boston), John Hershey (Winchester, Mass.), Zalan Borsos (Zurich), Marco Tagliasacchi (Ruvigliana, Switzerland), Neil Zeghidour (Paris) and Xuankai Chang (Pittsburgh).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system and method are disclosed. Audio input comprising the mixed audio signals is received by one or more client devices. The audio input is converted into a plurality of discrete tokens. A pl...