ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,738,266, issued on Sept. 15, was assigned to Beijing Zitiao Network Technology Co. Ltd. (Beijing) and Lemon Inc. (Grand Cayman, Cayman Islands).
"Improving speech recognition by a machine learning model" was invented by Pham Van Tung (Singapore), YiSheng Lin (Singapore), Han Tao (Singapore), Wei Li (Beijing), Jun Zhang (Beijing), Lu Lu (Los Angeles) and Yuxuan Wang (Los Angeles).
According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure describes techniques for improving speech recognition using a machine learning model. The machine learning model comprises a speech encoder configured to generate acoustic representations based on input speech...