US Patent Issued to GOOGLE on Nov. 3 for "Diffusion models for generation of audio data based on descriptive textual prompts" (American, Swiss Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,740, issued on Nov. 3, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Diffusion models for generation of audio data based on descriptive textual prompts" was invented by Qingqing Huang (Palo Alto, Calif.), Daniel Sung-Joon Park (Hoboken, N.J.), Aren Jansen (Mountain View, Calif.), Timo Immanuel Denk (Zurich, Switzerland), Yue Li (Mountain View, Calif.), Ravi Ganti (Santa Clara, Calif.), Dan Ellis (New York), Tao Wang (Sunnyvale, Calif.), Wei Han (Redwood City, Calif.) and Joonseok Lee (Fremont, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A corpus of textual data is generated with a machine-learned text generation model. The corpus of ...