ALEXANDRIA, Va., March 12 -- United States Patent no. 12,249,317, issued on March 11, was assigned to Google LLC (Mountain View, Calif.).

"Joint unsupervised and supervised training for multilingual ASR" was invented by Bo Li (Fremont, Calif.), Junwen Bai (Mountain View, Calif.), Yu Zhang (Mountain View, Calif.), Ankur Bapna (Sunnyvale, Calif.), Nikhil Siddhartha (Mountain View, Calif.), Khe Chai Sim (Dublin, Calif.) and Tara N. Sainath (Jersey City, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving audio features and generating a latent speech representation based on the audio features. The method also includes generating a target quantized vector token and a target token index...