ALEXANDRIA, Va., May 5 -- United States Patent no. 12,620,387, issued on May 5, was assigned to BEIJING BYTEDANCE NETWORK TECHNOLOGY Co. LTD. (Beijing).

"Voice generation method and apparatus, device, and computer readable medium" was invented by Meng Cai (Beijing) and Yalu Kong (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "A voice generation method and apparatus, an electronic device, and a computer readable storage medium. Said method comprises: performing speaker segmentation on an original voice to determine starting time and ending time of each speaking voice segment in the original voice, so as to obtain segmented voices; determining a voiceprint feature vector corresponding to each speaking ...