ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,499,876, issued on Dec. 16, was assigned to Amazon Technologies Inc. (Seattle).
"Multi-device speech processing" was invented by Rahul Gupta (Waltham, Mass.), Christophe Dupuy (Cambridge, Mass.), Jacob Ryan Stolee (Toronto) and Clement Chung (Toronto).
According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for partially processing an input on a device and completing processing at a remote system are provided. The device may process an input using an on-device machine learning (ML) model, and determine to cease processing at an intermediary node of the (ML) model based on the output of the intermediary node. Based on the output of the intermediary node ...