ALEXANDRIA, Va., May 5 -- United States Patent no. 12,620,404, issued on May 5, was assigned to Dolby Laboratories Licensing Corp. (San Francisco) and Dolby International AB (Dublin).
"Deep source separation architecture" was invented by Berkan Kadioglu (Boston), Michael Getty Horgan (Brewster, Mass.), Jordi Pons Puig (Catalunya, Spain) and Xiaoyu Liu (Dublin, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A speech separation server comprises a deep-learning encoder with nonlinear activation. The encoder is programmed to take a mixture audio waveform in the time domain, learn generalized patterns from the mixture audio waveform, and generate an encoded representation that effectively characterizes the...