ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,555,584, issued on Feb. 17, was assigned to Amazon Technologies Inc. (Seattle).
"Speaker diarization error correction" was invented by Sundararajan Srinivasan (Mountain View, Calif.), Rohit Paturi (Newark, Calif.), Katrin Kirchhoff (Seattle), Marc Helbing (Aachen, Germany), Sumit Kumar (Issaquah, Wash.) and Xiang Li (Cambridge, Great Britain).
According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for performing speaker error correction are described. In some examples, speaker error correction is a post-processing task to be performed on aligned predicted words and predicted one or more speaker identities to jointly perform speaker identities error cor...