公开(公告)号：US20210350074A1

公开(公告)日：2021-11-11

申请号：US17443330

申请日：2021-07-24

Applicant: Google LLC

Inventor： Evgeny A. Cherepanov ,  Gleb Skobeltsyn ,  Jakob Nicolaus Foerster ,  Petar Aleksic ,  Assaf Avner Hurwitz Michaely

IPC: G06F40/232 ,  G10L15/32 ,  G10L15/26 ,  G10L15/197 ,  G10L15/187 ,  G10L15/22 ,  G06F3/16 ,  G10L15/19 ,  G10L15/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

公开(公告)号：US20200168212A1

公开(公告)日：2020-05-28

申请号：US16751215

申请日：2020-01-24

Applicant: Google LLC

Inventor： Evgeny A Cherepanov ,  Gleb Skobeltsyn ,  Jakob Nicolaus Foerster ,  Petar Aleksic ,  Assaf Avner Hurwitz Michaely

IPC: G10L15/19 ,  G10L15/22 ,  G06F3/16 ,  G10L15/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing One of the methods includes receiving a first voice input from a user device, generating a first recognition output, receiving a user selection of one or more terms in the first recognition output- receiving a second voice input spelling a correction of the user selection, determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

公开(公告)号：US11797763B2

公开(公告)日：2023-10-24

申请号：US17443330

申请日：2021-07-24

Applicant: Google LLC

Inventor： Evgeny A. Cherepanov ,  Gleb Skobeltsyn ,  Jakob Nicolaus Foerster ,  Petar Aleksic ,  Assaf Avner Hurwitz Michaely

IPC: G10L15/22 ,  G10L15/01 ,  G10L15/24 ,  G06F40/232 ,  G10L15/32 ,  G10L15/26 ,  G10L15/197 ,  G10L15/187 ,  G06F3/16 ,  G10L15/19 ,  G10L15/30 ,  G10L15/08

CPC classification number: G06F40/232 ,  G06F3/167 ,  G10L15/187 ,  G10L15/19 ,  G10L15/197 ,  G10L15/22 ,  G10L15/26 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/086 ,  G10L2015/223

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

公开(公告)号：US11093710B2

公开(公告)日：2021-08-17

申请号：US16751215

申请日：2020-01-24

Applicant: Google LLC

Inventor： Evgeny A. Cherepanov ,  Gleb Skobeltsyn ,  Jakob Nicolaus Foerster ,  Petar Aleksic ,  Assaf Avner Hurwitz Michaely

IPC: G10L15/22 ,  G06F40/232 ,  G10L15/32 ,  G10L15/26 ,  G10L15/197 ,  G10L15/187 ,  G06F3/16 ,  G10L15/19 ,  G10L15/30 ,  G10L15/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing One of the methods includes receiving a first voice input from a user device, generating a first recognition output, receiving a user selection of one or more terms in the first recognition output- receiving a second voice input spelling a correction of the user selection, determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

公开(公告)号：US10229109B1

公开(公告)日：2019-03-12

申请号：US15700614

申请日：2017-09-11

Applicant: Google LLC

Inventor： Evgeny A. Cherepanov ,  Gleb Skobeltsyn ,  Jakob Nicolaus Foerster ,  Petar Aleksic ,  Assaf Avner Hurwitz Michaely

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/26 ,  G06F17/27 ,  G10L15/187 ,  G10L15/32 ,  G10L15/197 ,  G10L15/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.