US Patent Issued to NVIDIA on Sept. 2 for "Customizing text-to-speech language models using adapters for conversational AI systems and applications" (California Inventors)

ALEXANDRIA, Va., Sept. 3 -- United States Patent no. 12,406,653, issued on Sept. 2, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Customizing text-to-speech language models using adapters for conversational AI systems and applications" was invented by Cheng-Ping Hsieh (La Jolla, Calif.), Subhankar Ghosh (Santa Clara, Calif.) and Boris Ginsburg (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples, one or more text-to-speech machine learning models may be customized or adapted to accommodate new or additional speakers or speaker voices without requiring a full re-training of the models. For example, a base model may be trained on a set of one or more speakers and, after ...