US Patent Issued to Reality Defender on Nov. 4 for "Data-driven audio deepfake detection" (Canadian, American, Swiss Inventors)

ALEXANDRIA, Va., Nov. 6 -- United States Patent no. 12,462,813, issued on Nov. 4, was assigned to Reality Defender Inc. (New York).

"Data-driven audio deepfake detection" was invented by Gaurav Bharaj (Los Angeles), Petr Grinberg (Lausanne, Switzerland), Ankur Kumar (Los Angeles) and Surya Koppisetti (Coquitlam, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "An exemplary method for generating a visual representation of manipulations in an audio signal includes inputting the audio signal into a trained machine-learning model, wherein the machine-learning model is trained by generating, based on a training bona fide audio signal, a training bona fide time-frequency representation; generating, based on a...