US Patent Issued to Nvidia on March 31 for "Inferring emotion from speech in audio data using deep learning" (Russian Inventors)

ALEXANDRIA, Va., March 31 -- United States Patent no. 12,592,247, issued on March 31, was assigned to Nvidia Corp. (Santa Clara, Calif.).

"Inferring emotion from speech in audio data using deep learning" was invented by Ilia Federov (Moscow) and Dmitry Aleksandrovich Korobchenko (Moscow).

According to the abstract* released by the U.S. Patent & Trademark Office: "A deep neural network can be trained to infer emotion data from input audio. The network can be a transformer-based network that can infer probability values for a set of emotions or emotion classes. The emotion probability values can be modified using one or more heuristics, such as to provide for smoothing of emotion determinations over time, or via a user interface, where a us...