公开(公告)号：US10049655B1

公开(公告)日：2018-08-14

申请号：US14988074

申请日：2016-01-05

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/04 ,  G10L15/01 ,  G10L15/187 ,  G10L15/26

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US11881207B2

公开(公告)日：2024-01-23

申请号：US17656214

申请日：2022-03-23

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/22 ,  G10L15/14 ,  G10L13/00 ,  G10L15/01 ,  G10L15/187 ,  G10L15/26

CPC分类号： G10L15/01 ,  G10L15/187 ,  G10L15/22 ,  G10L15/26 ,  G10L2015/221

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US10242662B1

公开(公告)日：2019-03-26

申请号：US15789575

申请日：2017-10-20

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/22 ,  G10L15/30 ,  G10L15/01 ,  G10L15/26 ,  G10L15/187

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US10679609B2

公开(公告)日：2020-06-09

申请号：US16701685

申请日：2019-12-03

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/22 ,  G10L15/26 ,  G10L15/30 ,  G10L15/01 ,  G10L15/187

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US20200105247A1

公开(公告)日：2020-04-02

申请号：US16701685

申请日：2019-12-03

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/01 ,  G10L15/187 ,  G10L15/26

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US11302305B2

公开(公告)日：2022-04-12

申请号：US16874634

申请日：2020-05-14

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/22 ,  G10L15/32 ,  G10L15/26 ,  G10L15/01 ,  G10L15/187

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US10529316B1

公开(公告)日：2020-01-07

申请号：US16268957

申请日：2019-02-06

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G06F3/00 ,  G10L15/22 ,  G10L15/26 ,  G10L15/01 ,  G10L15/187

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US20230074406A1

公开(公告)日：2023-03-09

申请号：US17532794

申请日：2021-11-22

申请人： GOOGLE LLC

发明人： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Vikram Sridar ,  Daniel De Freitas Adiwardana ,  Noam M. Shazeer ,  Quoc Le

IPC分类号： G10L15/183 ,  G10L15/22

摘要： As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

公开(公告)号：US20220215828A1

公开(公告)日：2022-07-07

申请号：US17656214

申请日：2022-03-23

申请人： Google LLC

发明人： Evgeny A Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/01 ,  G10L15/187 ,  G10L15/22 ,  G10L15/26

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

公开(公告)号：US20210158796A1

公开(公告)日：2021-05-27

申请号：US16874634

申请日：2020-05-14

申请人： Google LLC

发明人： Evgeny A. Cherepanov ,  Jakob Nicolaus Foerster ,  Vikram Sridar ,  Ishai Rabinovitz ,  Omer Tabach

IPC分类号： G10L15/01 ,  G10L15/187 ,  G10L15/22 ,  G10L15/26

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.