ALEXANDRIA, Va., Feb. 24 -- United States Patent no. 12,562,184, issued on Feb. 24, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).
"Synthetic speech detection" was invented by Ke Wang (Beijing) and Lei He (Beijing).
According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for synthetic speech detection includes receiving an input sample comprising audio and extracting acoustic features corresponding to speech in the audio. The extracted acoustic features are processed using a plurality of neural networks to output abstracted features and generating a feature vector corresponding to the abstracted features using pooling. Training of an SSD task, a speaker classification task, and...