ALEXANDRIA, Va., July 9 -- United States Patent no. 12,354,600, issued on July 8, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Fast and efficient text only adaptation for factorized neural transducer" was invented by Rui Zhao (Bellevue, Wash.), Jian Xue (Bellevue, Wash.), Sarangarajan Parthasarathy (Mountain View, Calif.) and Jinyu Li (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods are provided for accessing a factorized neural transducer comprising a first set of layers for predicting blank tokens and a second set of layers for predicting vocabulary tokens, the second set of layers comprising a language model that includes a vocabulary predictor w...