US Patent Issued to Google on Sept. 15 for "Semantic segmentation with language models for long-form automatic speech recognition" (California, New York, New Jersey Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,738,264, issued on Sept. 15, was assigned to Google LLC (Mountain View, Calif.).

"Semantic segmentation with language models for long-form automatic speech recognition" was invented by Wenqian Huang (Mountain View, Calif.), Hao Zhang (Jericho, N.Y.), Shankar Kumar (New York), Shuo-yiin Chang (Sunnyvale, Calif.) and Tara N. Sainath (Jersey City, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A joint segmenting and ASR model includes an encoder to receive a sequence of acoustic frames and generate, at each of a plurality of output steps, a higher order feature representation for a corresponding acoustic frame. The model also includes a decoder to ge...