US Patent Issued to DOLBY LABORATORIES LICENSING on Oct. 28 for "Method and appartus for audio processing using a nested convolutional neural network architechture" (Chinese, American Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,456,481, issued on Oct. 28, was assigned to DOLBY LABORATORIES LICENSING Corp. (San Francisco).

"Method and appartus for audio processing using a nested convolutional neural network architechture" was invented by Jundai Sun (Beijing), Lie Lu (Dublin, Calif.) and Zhiwei Shuang (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, methods, and computer program products for audio processing based on convolutional neural network (CNN) are described. The CNN architecture may comprise a multi-scale input block and a multi-scale nested block. The multi-scale input block may be configured to receive input data and to generate a first downsampled inpu...