ALEXANDRIA, Va., Aug. 20 -- United States Patent no. 12,394,417, issued on Aug. 19, was assigned to Google LLC (Mountain View, Calif.).
"Cascaded audiovisual automatic speech recognition models" was invented by Oscar Chang (New York).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a sequence of acoustic frames and generating, by an audio encoder, at each of a plurality of output steps, an acoustic higher-order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. For each acoustic frame in the sequence of acoustic frames paired with a corresponding video frame, the method includes generating, by an audiovisual encoder, an audiovisual higher-or...