ALEXANDRIA, Va., July 23 -- United States Patent no. 12,367,344, issued on July 22, was assigned to Adobe Inc. (San Jose, Calif.).

"Curricular next conversation prediction pretraining for transcript segmentation" was invented by Anvesh Rao Vijjini (Chapel Hill, N.C.), Hanieh Deilamsalehy (Seattle) and Franck Dernoncourt (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing a transcript segmentation neural network to segment audio recording transcripts. In particular, in one or more embodiments, the disclosed systems implement a pretraining technique for a transcript segmentation neural ...