US Patent Issued to TENCENT AMERICA on Oct. 28 for "All deep learning minimum variance distortionless response beamformer for speech separation and enhancement" (Washington Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,456,457, issued on Oct. 28, was assigned to TENCENT AMERICA LLC (Palo Alto, Calif.).

"All deep learning minimum variance distortionless response beamformer for speech separation and enhancement" was invented by Yong Xu (Bellevue, Wash.), Meng Yu (Bellevue, Wash.), Shi-Xiong Zhang (Redmond, Wash.) and Dong Yu (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method, computer program, and computer system is provided for automated speech recognition. Audio data corresponding to one or more speakers is received. Covariance matrices of target speech and noise associated with the received audio data are estimated based on a gated recurrent uni...