US Patent Issued to NVIDIA on Sept. 1 for "Synthetic speech generation with flexible emotion control" (American, Indian Inventors)

ALEXANDRIA, Va., Sept. 1 -- United States Patent no. 12,725,605, issued on Sept. 1, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Synthetic speech generation with flexible emotion control" was invented by Siddharth Tyagi (Bangalore, India), Jason Conrad Roche (Santa Clara, Calif.) and Jose Rafael Valle Gomes da Costa (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed are apparatuses, systems, and techniques that may use machine learning for generating artificial speech. The techniques include generating a synthetic speech using a machine learning model-readable speech embedding associated with a target degree of an emotion and obtained by combining a plurality of reference spee...