US Patent Issued to Amazon Technologies on July 8 for "Efficient voice synthesis using frame-based processing" (American, German, Canadian Inventors)

ALEXANDRIA, Va., July 9 -- United States Patent no. 12,354,593, issued on July 8, was assigned to Amazon Technologies Inc. (Seattle).

"Efficient voice synthesis using frame-based processing" was invented by Ahmed Mustafa (Aachen, Germany), Jean-Marc Valin (Montreal), Jan Buethe (Munich), Paris Smaragdis (Urbana, Ill.) and Michael Mark Goodwin (Scotts Valley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Efficient voice synthesis using frame-based processing may be performed. An audio processing system converts an input speech waveform to an acoustic feature representation, which includes a sequence of frames at a lower resolution than the sampling resolution of the input waveform. The system propagat...