US Patent Issued to Google on May 27 for "Semi-supervised training scheme for speech recognition" (California, Washington Inventors)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,315,499, issued on May 27, was assigned to Google LLC (Mountain View, Calif.).

"Semi-supervised training scheme for speech recognition" was invented by Soheil Khorram (Redwood City, Calif.), Anshuman Tripathi (Mountain View, Calif.), Kim Jaeyoung (Cupertino, Calif.), Han Lu (Redmond, Wash.), Qian Zhang (Mountain View, Calif.) and Hasim Sak (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. The method also includes generating, using a supervised audio encod...