ALEXANDRIA, Va., Feb. 5 -- United States Patent no. 12,217,745, issued on Feb. 4, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Unified speech representation learning" was invented by Yao Qian (Bellevue, Wash.), Yu Wu (Beijing), Kenichi Kumatani (Sammamish, Wash.), Shujie Liu (Beijing), Furu Wei (Beijing), Nanshan Zeng (Bellevue, Wash.), Xuedong David Huang (Yarrow Point, Wash.) and Chengyi Wang (Jinan, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system obtains a first training data set comprising labeled speech data or both labeled and unlabeled data corresponding to a high-resource data set as well as latent speech representations based on the first training data set. The...