US Patent Issued to Google on June 9 for "Streaming speech-to-speech model with automatic speaker turn detection" (California Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,651,591, issued on June 9, was assigned to Google LLC (Mountain View, Calif.).

"Streaming speech-to-speech model with automatic speaker turn detection" was invented by Fadi Biadsy (Mountain View, Calif.) and Oleg Rybakov (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for turn detection in a speech-to-speech model includes receiving, as input to the speech-to-speech (S2S) model, a sequence of acoustic frames corresponding to an utterance. The method further includes, at each of a plurality of output steps, generating, by an audio encoder of the S2S model, a higher order feature representation for a corresponding acoustic fr...