ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,896, issued on Nov. 18, was assigned to Zhejiang Gongshang University (Hangzhou, China).

"Method for cross-domain speech deepfake detection" was invented by Shouguang Wang (Hangzhou, China), Pu Huang (Hangzhou, China) and Mengchu Zhou (Hangzhou, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for detecting speech deepfakes under real-world conditions is disclosed, where factors such as audio compression, transmission channels, and codec transformations may distort the speech signal. The invention combines self-supervised learning pre-trained models, domain-invariant representation learning, and one-class learning to improve the robustn...