ALEXANDRIA, Va., Dec. 23 -- United States Patent no. 12,505,849, issued on Dec. 23, was assigned to Synaptics Inc. (San Jose, Calif.).
"Multi-pass neural network for speech enhancement" was invented by Saeed Mosayyebpour Kaskari (Irvine, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure provides methods, devices, and systems for audio signal processing. The present implementations more specifically relate to multi-pass neural networks configured for speech enhancement. In some aspects, a speech enhancement system may include a deep neural network (DNN) and a statistical signal processor (SSP). The DNN is configured to receive an input audio signal and infer a speech signal representing a ...