ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,552, issued on March 24, was assigned to Adobe Inc. (San Jose, Calif.).
"Multi-level audio segmentation using deep embeddings" was invented by Justin Salamon (San Francisco), Oriol Nieto-Caballero (Oakland, Calif.) and Nicholas J. Bryan (Belmont, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments are disclosed for generating an audio segmentation of an audio sequence using deep embeddings. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including an audio sequence and extracting features for each frame of the audio sequence, where each frame is associated with a beat of the aud...