ALEXANDRIA, Va., Feb. 19 -- United States Patent no. 12,230,259, issued on Feb. 18, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).
"Array geometry agnostic multi-channel personalized speech enhancement" was invented by Sefik Emre Eskimez (Bellevue, Wash.), Takuya Yoshioka (Bellevue, Wash.), Huaming Wang (Clyde Hill, Wash.), Hassan Taherian (Columbus, Ohio), Zhuo Chen (Redmond, Wash.) and Xuedong Huang (Redmond, Wash.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Examples of array geometry agnostic multi-channel personalized speech enhancement (PSE) extract speaker embeddings, which represent acoustic characteristics of one or more target speakers, from target speaker enrollment data. S...