US Patent Issued to Naro on March 3 for "Text to audio conversion with disentangled style conditioning" (Japanese, Canadian Inventors)

ALEXANDRIA, Va., March 3 -- United States Patent no. 12,567,421, issued on March 3, was assigned to Naro Corp. (West Bloomfield, Mich.).

"Text to audio conversion with disentangled style conditioning" was invented by Lyle Patrick Stein (Toronto), Max Florian Frenzel (Tokyo) and Todd Silverstein (Tokyo).

According to the abstract* released by the U.S. Patent & Trademark Office: "A style encoder can be trained to encode audio style and audio characteristics into selected regions of a style vector. The style vector can be used to condition a text to speech (TTS) model to generate speech with human-understandable and controllable styles. Various training strategies of the style encoder are described, including a first, second and third traini...