US Patent Issued to HANGZHOU TONGHUASHUN DATA PROCESSING on Aug. 11 for "End-to-end natural and controllable emotional speech synthesis methods" (Chinese Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,706,080, issued on Aug. 11, was assigned to HANGZHOU TONGHUASHUN DATA PROCESSING Co. LTD. (Hangzhou, China).

"End-to-end natural and controllable emotional speech synthesis methods" was invented by Ming Chen (Hangzhou, China), Xinkang Xu (Hangzhou, China), Xinhui Hu (Hangzhou, China) and Xudong Zhao (Hangzhou, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure provides acoustic model training methods and systems, and speech synthesis methods and systems. An acoustic model training method may include obtaining a plurality of training samples. Each of the plurality of training samples may include a sample text input, a sample emot...