US Patent Issued to Google on Feb. 10 for "Universal monolingual output layer for multilingual speech recognition" (California, New Jersey Inventors)

ALEXANDRIA, Va., Feb. 11 -- United States Patent no. 12,548,561, issued on Feb. 10, was assigned to Google LLC (Mountain View, Calif.).

"Universal monolingual output layer for multilingual speech recognition" was invented by Chao Zhang (Mountain View, Calif.), Bo Li (Santa Clara, Calif.), Tara N. Sainath (Jersey City, N.J.), Trevor Strohman (Mountain View, Calif.) and Shuo-yiin Chang (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a sequence of acoustic frames as input to a multilingual automated speech recognition (ASR) model configured to recognize speech in a plurality of different supported languages and generating, by an audio encoder of the multilingual ASR...