US Patent Issued to Google on Feb. 25 for "Separating speech by source in audio recordings by predicting isolated audio signals conditioned on speaker representations" (American, French Inventors)

ALEXANDRIA, Va., Feb. 26 -- United States Patent no. 12,236,970, issued on Feb. 25, was assigned to Google LLC (Mountain View, Calif.).

"Separating speech by source in audio recordings by predicting isolated audio signals conditioned on speaker representations" was invented by Neil Zeghidour (Paris) and David Grangier (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing speech separation. One of the methods includes obtaining a recording comprising speech from a plurality of speakers; processing the recording using a speaker neural network having speaker parameter values and configu...