US Patent Issued to SONY GROUP on July 22 for "Visual speech recognition based on connectionist temporal classification loss" (California Inventors)

ALEXANDRIA, Va., July 23 -- United States Patent no. 12,367,881, issued on July 22, was assigned to SONY GROUP Corp. (Tokyo).

"Visual speech recognition based on connectionist temporal classification loss" was invented by Shiwei Jin (San Diego), Jong Hwa Lee (San Diego), Matthew Wnuk (San Diego) and Francisco Costela (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "An electronic apparatus and method for visual speech recognition based on connectionist temporal classification (CTC) loss is disclosed. The electronic apparatus receives a video that includes human speakers and generates a prediction corresponding to lip movements of the human speakers. The prediction is generated based on application of...