ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,890, issued on July 14, was assigned to Google LLC (Mountain View, Calif.).

"Mask-conformer augmenting conformer with mask-predict decoder unifying speech recognition and rescoring" was invented by Andrew M. Rosenberg (Brooklyn, N.Y.), Yosuke Higuchi (Mountain View, Calif.) and Bhuvana Ramabhadran (Mt. Kisco, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a sequence of acoustic frames characterizing an utterance. During a first pass, the method includes generating first-pass audio encodings based on the sequence of acoustic frames using a stack of mask-conformer blocks of an acoustic encoder, generating a first-pass ...