US Patent Issued to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE on Nov. 3 for "Multi-modality voice recognition device and method" (South Korean Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,741, issued on Nov. 3, was assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE (Daejeon, South Korea).

"Multi-modality voice recognition device and method" was invented by Yoonhyung Kim (Daejeon, South Korea), Byung Ok Kang (Daejeon, South Korea), Hwa Jeon Song (Daejeon, South Korea) and Inkyu An (Daejeon, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "A multi-modality voice recognition device is provided. The multi-modality voice recognition device includes a video encoder trained to receive a lip video to a video encoder to extract visual feature information for voice recognition, an audio encoder trained to receive a voic...