ALEXANDRIA, Va., Oct. 27 -- United States Patent no. 12,776,303, issued on Oct. 27, was assigned to MICROSOFT TECHNOLOGY LICENSING LLC (Redmond, Wash.).
"Multi-encoder end-to-end automatic speech recognition (ASR) for joint modeling of multiple input devices" was invented by Felix Weninger (Cambridge, Mass.), Marco Gaudesi (Turin, Italy), Ralf Leibold (Julich, Germany) and Puming Zhan (Acton, Mass.).
According to the abstract* released by the U.S. Patent & Trademark Office: "An end-to-end automatic speech recognition (ASR) system includes: a first encoder configured for close-talk input captured by a close-talk input mechanism; a second encoder configured for far-talk input captured by a far-talk input mechanism; and an encoder selection ...