US Patent Issued to QUALCOMM on Aug. 4 for "Audio coding using machine learning based linear filters and non-linear neural sources" (Dutch, American Inventors)

ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,700,415, issued on Aug. 4, was assigned to QUALCOMM Inc. (San Diego).

"Audio coding using machine learning based linear filters and non-linear neural sources" was invented by Guillaume Konrad Sautiere (Amsterdam), Duminda Dewasurendra (San Diego), Zisis Iason Skordilis (San Diego) and Vivek Rajendran (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and techniques are described for coding audio signals. For example, a voice decoder can generate, using a first neural network, an excitation signal for at least one sample of an audio signal at least in part by performing a non-linear operation based on one or more inputs to the first neural ...