ALEXANDRIA, Va., June 12 -- United States Patent no. 12,300,220, issued on May 13, was assigned to NANJING SILICON INTELLIGENCE TECHNOLOGY Co. LTD. (Jiangsu, China).

"Pitch-based speech conversion model training method and speech conversion system" was invented by Huapeng Sima (Jiangsu, China) and Ran Xu (Jiangsu, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure provides a pitch-based speech conversion model training method and a speech conversion system, wherein an audio feature code is output by a priori encoder, and a pitch feature is extracted by a pitch extraction module. A linear spectrum corresponding to the reference speech is input into the posteriori encoder to obtain an ...