US Patent Issued to Google on June 3 for "Predicting word boundaries for on-device batching of end-to-end speech recognition models" (California, New Jersey Inventors)

ALEXANDRIA, Va., June 4 -- United States Patent no. 12,322,383, issued on June 3, was assigned to Google LLC (Mountain View, Calif.).

"Predicting word boundaries for on-device batching of end-to-end speech recognition models" was invented by Shaan Jagdeep Patrick Bijwadia (San Francisco), Tara N. Sainath (Jersey City, N.J.), Jiahui Yu (Mountain View, Calif.), Shuo-yiin Chang (Sunnyvale, Calif.) and Yangzhang He (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a sequence of input audio frames corresponding to an utterance captured by a user device, the utterance including a plurality of words. For each input audio frame, the method includes predicting, using a ...