US Patent Issued to BEIJING YOUZHUJU NETWORK TECHNOLOGY on Jan. 27 for "Model training method, speech recognition method, device, medium, and apparatus" (Chinese Inventors)

ALEXANDRIA, Va., Jan. 28 -- United States Patent no. 12,536,990, issued on Jan. 27, was assigned to BEIJING YOUZHUJU NETWORK TECHNOLOGY Co. LTD. (Beijing).

"Model training method, speech recognition method, device, medium, and apparatus" was invented by Linhao Dong (Beijing) and Zejun Ma (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "A model training method, a speech recognition method and apparatus, a medium, and a device are provided. The speech recognition model including an encoder, a CIF prediction sub-model and a CTC prediction sub-model. The model training method includes: encoding training speech data based on the encoder to obtain an acoustic vector sequence corresponding to the training sp...