US Patent Issued to Google on March 17 for "Automatic speech recognition accuracy with multimodal embeddings search" (American, Chinese Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,995, issued on March 17, was assigned to Google LLC (Mountain View, Calif.).

"Automatic speech recognition accuracy with multimodal embeddings search" was invented by Christopher Li (New York), Kyle Scott Kastner (Waltham, Mass.), Yuan Wang (Hoboken, N.J.), Zhehuai Chen (Edgewater, N.J.), Andrew Maxwell Rosenberg (Brooklyn, N.Y.), Heng Su (Beijing), Qian Chen (Beijing), Leonid Aleksandrovich Velikovich (New York), Patrick Maxim Rondon (New York), Diamantino Antonio Caseiro (Philadelphia) and Zelin Wu (Jersey City, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving training data that includes a set of transcribed speech ...