ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,744,029, issued on Sept. 22, was assigned to Google LLC (Mountain View, Calif.).
"Phonemes and graphemes for neural text-to-speech" was invented by Ye Jia (Mountain View, Calif.), Byungha Chun (Tokyo), Yu Zhang (Mountain View, Calif.), Jonathan Shen (Mountain View, Calif.) and Yonghui Wu (Fremont, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes receiving a text input including a sequence of words represented as an input encoder embedding. The input encoder embedding includes a plurality of tokens, with the plurality of tokens including a first set of grapheme tokens representing the text input as respective graphemes and a secon...