US Patent Issued to DeepMind Technologies on Jan. 28 for "Speech synthesis utilizing audio waveform difference signal(s)" (American, Dutch Inventors)

ALEXANDRIA, Va., Jan. 29 -- United States Patent no. 12,211,484, issued on Jan. 28, was assigned to DeepMind Technologies Ltd. (London).

"Speech synthesis utilizing audio waveform difference signal(s)" was invented by Luis Carlos Cobo Rus (San Francisco), Nal Kalchbrenner (Amsterdam), Erich Elsen (Naperville, Ill.) and Chenjie Gu (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level ...