公开(公告)号：US11531736B1

公开(公告)日：2022-12-20

申请号：US16357003

申请日：2019-03-18

Applicant: Amazon Technologies, Inc.

Inventor： Angela Sun ,  Vikram Kumar Gundeti ,  Max David Klein ,  John Charles Howard

IPC: H04L29/06 ,  G06F21/32 ,  G10L17/22 ,  G06F21/45 ,  G10L17/00

Abstract: Systems, methods, and devices for adaptably authenticating a user are disclosed. A device captures a user input, and sends data corresponding thereto to a system. The system determines natural language understanding (NLU) results representing the user input. A user authentication component of the system receives the NLU results and determines a skill configured to perform an action responsive to the user input. The user authentication component adaptably performs user authentication based on a user authentication condition associated with the skill. If the user can be authenticated to the satisfaction of the condition, the NLU results data are sent to the skill, along with an indicator representing the user was authenticated by the system.

公开(公告)号：US11211058B1

公开(公告)日：2021-12-28

申请号：US16577394

申请日：2019-09-20

Applicant: Amazon Technologies, Inc.

Inventor： Aaron Eakin ,  Angela Sun ,  Ankur Gandhe ,  Ariya Rastrow ,  Chenlei Guo ,  Xing Fan

IPC: G10L15/197 ,  G10L15/30 ,  G10L15/22

Abstract: Described herein is a system for prompting a user for clarification when an automatic speech recognition (ASR) system encounters ambiguity with respect to the user's input. The feedback provided by the user is used to retrain machine-learning models and/or to generate new machine-learning models. Based on the type of ambiguity, the system may determine to retrain one or more ASR models that are widely used by the system or to generate/update one or more user-specific models that are used to process inputs from one or more particular users.