ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,706,091, issued on Aug. 11, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Pronunciation-aware embedding generation for conversational AI systems and applications" was invented by Hainan Xu (New York), Boris Ginsburg (Sunnyvale, Calif.), Zhehuai Chen (Odessa, Fla.) and Fei Jia (Santa Clara, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "One or more embodiments include: receiving a first frame of acoustic input and one or more prior textual tokens associated with a prior frame of the acoustic input, wherein the prior textual token represents one or more spoken word included in the acoustic input; generating a multi-dimensional embedding asso...