US Patent Issued to Microsoft Technology Licensing on Feb. 3 for "Training and using a transcript generation model on a multi-speaker audio stream" (Washington Inventors)

ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,542,134, issued on Feb. 3, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Training and using a transcript generation model on a multi-speaker audio stream" was invented by Naoyuki Kanda (Bellevue, Wash.), Takuya Yoshioka (Bellevue, Wash.), Zhuo Chen (Bellevue, Wash.), Jinyu Li (Sammamish, Wash.), Yashesh Gaur (Redmond, Wash.), Zhong Meng (Mercer Island, Wash.), Xiaofei Wang (Bellevue, Wash.) and Xiong Xiao (Bothell, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The disclosure herein describes using a transcript generation model for generating a transcript from a multi-speaker audio stream. Audio data including overlapping sp...