US Patent Issued to Google on Sept. 8 for "Attention-based joint acoustic and text on-device end-to-end model" (New York, California, New Jersey Inventors)

ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,575, issued on Sept. 8, was assigned to Google LLC (Mountain View, Calif.).

"Attention-based joint acoustic and text on-device end-to-end model" was invented by Tara N. Sainath (Jersey City, N.J.), Ruoming Pang (New York), Ron Weiss (New York), Yanzhang He (Mountain View, Calif.), Chung-cheng Chiu (Sunnyvale, Calif.) and Trevor Strohman (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a training example for a listen-attend-spell (LAS) decoder of a two-pass streaming neural network model and determining whether the training example corresponds to a supervised audio-text pair or an unpaired text sequenc...