US Patent Issued to Industry-University Cooperation Foundation Hanyang University on Jan. 27 for "Method and device for speech synthesis based on multi-speaker training data sets" (South Korean Inventors)

ALEXANDRIA, Va., Jan. 28 -- United States Patent no. 12,536,987, issued on Jan. 27, was assigned to Industry-University Cooperation Foundation Hanyang University (Seoul, South Korea).

"Method and device for speech synthesis based on multi-speaker training data sets" was invented by Joon Hyuk Chang (Seoul, South Korea) and Jae Uk Lee (Seoul, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "An exemplary embodiment of the present disclosure is a speech synthesis method based on multi-speaker training dataset of a speech synthesis apparatus including pre-training a speech synthesis model using a previously stored neural network with a single speaker training dataset with most spoken sentences, among tr...