US Patent Issued to Amazon Technologies on March 24 for "Multi-domain fine-tuning for contextual adapters of automatic speech recognition" (American, Canadian Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,567, issued on March 24, was assigned to Amazon Technologies Inc. (Seattle).

"Multi-domain fine-tuning for contextual adapters of automatic speech recognition" was invented by Devang Kulshreshtha (Montreal), Saket Dingliwal (Kirkland, Wash.), Brady Houston (Bothell, Wash.), Sravan Babu Bodapati (Fremont, Calif.), Srikanth Ronanki (San Jose, Calif.), Jeffrey John Farris (Crystal Lake, Ill.), Vivek Govindan (Black Diamond, Wash.) and Katrin Kirchhoff (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Multi-stage fine-tuning for customizing automatic speech recognition with contextual adapters is performed. Entities to customize automatic speech ...