US Patent Issued to Google on Aug. 26 for "Using aligned text and speech representations to train automatic speech recognition models without transcribed speech data" (New York, New Jersey, California Inventors)

ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,400,638, issued on Aug. 26, was assigned to Google LLC (Mountain View, Calif.).

"Using aligned text and speech representations to train automatic speech recognition models without transcribed speech data" was invented by Andrew Rosenberg (Brooklyn, N.Y.), Zhehuai Chen (Edgewater, N.J.), Ankur Bapna (Sunnyvale, Calif.), Yu Zhang (Mountain View, Calif.) and Bhuvana Ramabhadran (Mt. Kisco, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving training data that includes unspoken textual utterances in a target language. Each unspoken textual utterance not paired with any corresponding spoken utterance of non-synthetic speech. The m...