ALEXANDRIA, Va., Dec. 23 -- United States Patent no. 12,505,317, issued on Dec. 23, was assigned to OpenAI Opco LLC (San Francisco).
"Multi-task automatic speech recognition system" was invented by Alec Radford (San Francisco), Jong Wook Kim (San Francisco), Tao Xu (San Francisco), Greg Brockman (San Francisco), Christine McLeavey-Payne (San Francisco) and Ilya Sutskever (San Francisco).
According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed herein are methods, systems, and computer-readable media for generating an output transcript from an input audio segment using a multi-task transformer model. In some embodiments, the transformer model can be trained to transcribe or translate audio data in multiple lang...