ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,991, issued on March 17, was assigned to DOLBY INTERNATIONAL AB (Dublin).
"Generative neural network model for processing audio samples in a filter-bank domain" was invented by Per Ekstrand (Saltsjobaden, Sweden), Janusz Klejsa (Solna, Sweden), Pedro Jafeth Villasana Tinajero (Sundbyberg, Sweden) and Lars Villemoes (Jarfalla, Sweden).
According to the abstract* released by the U.S. Patent & Trademark Office: "A neural network system is provided, implementing a generative model for autoregressively generating a distribution for a plurality of current filter-bank samples of an audio signal, wherein the current samples correspond to a current time slot, and each current sample corr...