US Patent Issued to Amazon Technologies on Oct. 21 for "Federated learning for audio processing" (Massachusetts, Vermont Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,451,122, issued on Oct. 21, was assigned to Amazon Technologies Inc. (Seattle).

"Federated learning for audio processing" was invented by Andrew Morris Werchniak (Boston), Ilya Sokolov (Boston), Raphael Petegrosso (Cambridge, Mass.), Aansh Shah (Cambridge, Mass.), Aaron Challenner (Melrose, Mass.), Michael Thomas Peterson (Watertown, Mass.) and Shuang Wu (Shelburne, Vt.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system performs federated learning and retraining of a machine learning model used for processing audio detected by a user device. The system uses both gradient data (which may correspond to false-rejects) and audio data (which may corresp...