US Patent Issued to Amazon Technologies on Jan. 20 for "Semi-supervised training of a machine learning model for target speaker audio enhancement" (American, Canadian Inventors)

ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,531,067, issued on Jan. 20, was assigned to Amazon Technologies Inc. (Seattle).

"Semi-supervised training of a machine learning model for target speaker audio enhancement" was invented by Ritwik Giri (Mountain View, Calif.), Michael Mark Goodwin (Scotts Valley, Calif.), Arvindh Krishnaswamy (Palo Alto, Calif.), Mehmet Umut Isik (White Plains, N.Y.), Jean-Marc Valin (Montreal), Zhepei Wang (Champaign, Ill.), Shrikant Venkataramani (Champaign, Ill.) and Paris Smaragdis (Urbana, Ill.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Training a machine learning model for application to an audio enhancement system for a target speaker may be performed. When at ...