公开(公告)号：US20230386652A1

公开(公告)日：2023-11-30

申请号：US18234350

申请日：2023-08-15

Applicant: Google LLC

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G16H40/20 ,  G10L15/26 ,  G10L15/18 ,  G06F40/47 ,  G06F40/58 ,  G10L15/06 ,  G10L15/14 ,  G10L15/16 ,  G10L15/183

CPC classification number: G16H40/20 ,  G10L15/26 ,  G10L15/1822 ,  G06F40/47 ,  G06F40/58 ,  G10L15/063 ,  G10L15/142 ,  G10L15/16 ,  G10L15/183

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

公开(公告)号：US10860685B2

公开(公告)日：2020-12-08

申请号：US15362643

申请日：2016-11-28

Applicant: Google LLC

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G10L15/26 ,  G06F19/00 ,  G10L15/18 ,  G06F40/47 ,  G06F40/58 ,  G10L15/06 ,  G10L15/14 ,  G10L15/16 ,  G10L15/183

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

公开(公告)号：US11763936B2

公开(公告)日：2023-09-19

申请号：US17112279

申请日：2020-12-04

Applicant: Google LLC

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G10L15/26 ,  G16H40/20 ,  G10L15/18 ,  G06F40/47 ,  G06F40/58 ,  G10L15/06 ,  G10L15/14 ,  G10L15/16 ,  G10L15/183

CPC classification number: G16H40/20 ,  G06F40/47 ,  G06F40/58 ,  G10L15/063 ,  G10L15/142 ,  G10L15/16 ,  G10L15/183 ,  G10L15/1822 ,  G10L15/26

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

公开(公告)号：US20210090724A1

公开(公告)日：2021-03-25

申请号：US17112279

申请日：2020-12-04

Applicant: Google LLC

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G16H40/20 ,  G06F40/47 ,  G10L15/18 ,  G10L15/183 ,  G10L15/16 ,  G10L15/26 ,  G06F40/58 ,  G10L15/14 ,  G10L15/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.