US Patent Issued to TENCENT AMERICA on July 8 for "Techniques for disentangled variational speech representation learning for zero-shot voice conversion" (California Inventors)

ALEXANDRIA, Va., July 9 -- United States Patent no. 12,354,594, issued on July 8, was assigned to TENCENT AMERICA LLC (Palo Alto, Calif.).

"Techniques for disentangled variational speech representation learning for zero-shot voice conversion" was invented by Chunlei Zhang (Palo Alto, Calif.), Jiachen Lian (Palo Alto, Calif.) and Dong Yu (Palo Alto, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for disentangled variational speech representation learning for voice conversion, performed by at least one processor, is provided. The method includes receiving input speech segments, encoding the input speech segments via a shared encoder to generate a speaker embedding and a content embedding, encod...