ALEXANDRIA, Va., May 1 -- United States Patent no. 11,972,754, issued on April 30, was assigned to TENCENT AMERICA LLC (Palo Alto, Calif.).
"Multi-task training architecture and strategy for attention-based speech recognition system" was invented by Jia Cui (Bellevue, Wash.), Chao Weng (Fremont, Calif.), Guangsen Wang (Shenzhen, China), Jun Wang (Shenzhen, China), Chengzhu Yu (Bellevue, Wash.), Dan Su (Shenzhen, China) and Dong Yu (Bothell, Wash.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and apparatuses are provided for performing sequence to sequence (Seq2Seq) speech recognition training performed by at least one processor. The method includes acquiring a training set comprising a plurality of ...