ALEXANDRIA, Va., July 3 -- United States Patent no. 12,347,438, issued on July 1, was assigned to Google LLC (Mountain View, Calif.).

"Optimizing personal VAD for on-device speech recognition" was invented by Shaojin Ding (Mountain View, Calif.), Rajeev Rikhye (Mountain View, Calif.), Qiao Liang (Mountain View, Calif.), Yanzhang He (Palo Alto, Calif.), Quan Wang (Hoboken, N.J.), Arun Narayanan (Santa Clara, Calif.), Tom O'malley (Mountain View, Calif.) and Ian Mcgraw (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method includes receiving a sequence of acoustic frames corresponding to an utterance and generating a reference speaker embedding for the utterance. Th...