US Patent Issued to ASAPP on Feb. 3 for "Text-to-audio conversion with byte-encoding vectors" (New York, Washington, California Inventors)

ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,542,127, issued on Feb. 3, was assigned to ASAPP INC. (New York).

"Text-to-audio conversion with byte-encoding vectors" was invented by Justin Robert Lovelace (Ithaca, N.Y.), Soham Ray (Ithaca, N.Y.), Felix Wu (Issaquah, Wash.), Kilian Quirin Weinberger (Ithaca, N.Y.) and Kwangyoun Kim (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A diffusion model may be used to generate an audio signal from text. The diffusion model may process received text and noise vectors to compute encoded audio vectors that correspond to the text. The encoded audio vectors may be decoded to generate an audio signal of a person speaking the text that may be pres...