US Patent Issued to ASAPP on June 23 for "Training speech processing models using pseudo tokens" (American, British Inventors)

ALEXANDRIA, Va., July 15 -- United States Patent no. 12,664,974, issued on June 23, was assigned to ASAPP INC. (New York).

"Training speech processing models using pseudo tokens" was invented by Felix Wu (Ithaca, N.Y.), Kwangyoun Kim (Santa Clara, Calif.), Ryan Thomas McDonald (London), Kilian Quirin Weinberger (Ithaca, N.Y.), Kyu Jeong Han (Pleasanton, Calif.) and Yoav Artzi (New York).

According to the abstract* released by the U.S. Patent & Trademark Office: "A speech processing model may be trained using pseudo tokens. Training a speech processing model with pseudo tokens may allow for training with a smaller amount of labeled training data and accordingly lower costs. A set of pseudo tokens may be determined by computing feature vect...