US Patent Issued to Zoom Communications on May 26 for "Semi-supervised training of automatic speech recognition systems using iterative n -best pseudo-labeling" (German, Chinese Inventors)

ALEXANDRIA, Va., May 26 -- United States Patent no. 12,640,141, issued on May 26, was assigned to Zoom Communications Inc. (San Jose, Calif.).

"Semi-supervised training of automatic speech recognition systems using iterative n -best pseudo-labeling" was invented by Juan Hussain (Worth am Rhein, Germany), Thai Son Nguyen (Karlsruhe, Germany), Sebastian Stuker (Karlsruhe, Germany) and Zhirong Ye (Hangzhou, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "One example method includes generating teacher and student ASR models from an ASR model; generating a plurality of successive generations of the teacher ASR model, including: generating, for each unannotated audio sample of a training data set, one or more...