US 12,431,117 B2
Electroencephalograph signal generation speech in a generative adversarial network
Erhan Bilal, Westport, CT (US); Chen Wang, Chappaqua, NY (US); and Bo Wen, New York, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jun. 27, 2023, as Appl. No. 18/341,867.
Prior Publication US 2025/0006174 A1, Jan. 2, 2025
Int. Cl. G10L 13/04 (2013.01)
CPC G10L 13/04 (2013.01) 20 Claims
OG exemplary drawing
 
1. A computer implemented method for synthesizing electroencephalograph signals, the computer implemented method comprising:
creating, by a number of processor units, a training dataset comprising real electroencephalograph signals, speech signals correlating to the real electroencephalograph signals, and a set of human characteristics for the real electroencephalograph signals; and
training, by the number of processor units, a generative adversarial network using the training dataset to create a trained generative adversarial network, wherein the trained generative adversarial network generates synthetic electroencephalograph signals in response to receiving new speech signals.