公开(公告)号：US11908480B1

公开(公告)日：2024-02-20

申请号：US16826950

申请日：2020-03-23

Applicant: Amazon Technologies, Inc.

Inventor： Da Teng ,  Adrian Evans ,  Naresh Narayanan

IPC: G10L17/00 ,  G10L17/06

CPC classification number: G10L17/00 ,  G10L17/06

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

公开(公告)号：US20250131921A1

公开(公告)日：2025-04-24

申请号：US18817461

申请日：2024-08-28

Applicant: Amazon Technologies, Inc.

Inventor： Da Teng ,  Adrian Evans ,  Naresh Narayanan

IPC: G10L15/183 ,  G10L15/22 ,  G10L17/22

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

公开(公告)号：US11386887B1

公开(公告)日：2022-07-12

申请号：US16827025

申请日：2020-03-23

Applicant: Amazon Technologies, Inc.

Inventor： Da Teng ,  Adrian Evans ,  Naresh Narayanan

IPC: G10L15/183 ,  G10L15/22 ,  G10L17/22

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

公开(公告)号：US12080282B2

公开(公告)日：2024-09-03

申请号：US17848901

申请日：2022-06-24

Applicant: Amazon Technologies, Inc.

Inventor： Da Teng ,  Adrian Evans ,  Naresh Narayanan

IPC: G10L15/183 ,  G10L15/22 ,  G10L17/22

CPC classification number: G10L15/183 ,  G10L15/22 ,  G10L17/22 ,  G10L2015/223 ,  G10L2015/227 ,  G10L2015/228

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

公开(公告)号：US20230042420A1

公开(公告)日：2023-02-09

申请号：US17848901

申请日：2022-06-24

Applicant: Amazon Technologies, Inc.

Inventor： Da Teng ,  Adrian Evans ,  Naresh Narayanan

IPC: G10L15/183 ,  G10L17/22 ,  G10L15/22

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.