ALEXANDRIA, Va., Nov. 6 -- United States Patent no. 12,462,793, issued on Nov. 4, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Speech recognition hypothesis generation according to previous occurrences of hypotheses terms and/or contextual data" was invented by Agoston Weisz (Zurich), Alexandru Dovlecel (Zurich), Gleb Skobeltsyn (Kilchberg, Switzerland), Evgeny Cherepanov (Adliswil, Switzerland), Justas Klimavicius (Zurich), Yihui Ma (Zurich) and Lukas Lopatovsky (Kilchberg, Switzerland).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations set forth herein relate to speech recognition techniques for handling variations in speech among users (e.g. due to different accents) and processing feat...