US Patent Issued to Unity Technologies SF on May 27 for "Speaker separation based on real-time latent speaker state characterization" (Swiss Inventors)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,315,516, issued on May 27, was assigned to Unity Technologies SF (San Francisco).

"Speaker separation based on real-time latent speaker state characterization" was invented by Valentin Alain Jean Perret (Zurich), Nandor Kedves (Adliswil, Switzerland) and Nicolas Lucien Perony (Zurich).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, methods, and non-transitory computer-readable media can obtain a stream of audio waveform data that represents speech involving a plurality of speakers. As the stream of audio waveform data is obtained, a plurality of audio chunks can be determined. An audio chunk can be associated with one or more identity embeddings....