公开(公告)号：US10885898B2

公开(公告)日：2021-01-05

申请号：US15711260

申请日：2017-09-21

Applicant: Google LLC

Inventor： Petar Aleksic ,  Glen Shires ,  Michael Buchanan

IPC: G10L15/04 ,  G10L15/05 ,  G10L15/22 ,  G10L15/26 ,  G10L15/08 ,  G06F3/16 ,  G10L25/78

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data including an utterance, obtaining context data that indicates one or more expected speech recognition results, determining an expected speech recognition result based on the context data, receiving an intermediate speech recognition result generated by a speech recognition engine, comparing the intermediate speech recognition result to the expected speech recognition result for the audio data based on the context data, determining whether the intermediate speech recognition result corresponds to the expected speech recognition result for the audio data based on the context data, and setting an end of speech condition and providing a final speech recognition result in response to determining the intermediate speech recognition result matches the expected speech recognition result, the final speech recognition result including the one or more expected speech recognition results indicated by the context data.

公开(公告)号：US20210312903A1

公开(公告)日：2021-10-07

申请号：US17353764

申请日：2021-06-21

Applicant: Google LLC

Inventor： Siddhi Tadpatrikar ,  Michael Buchanan ,  Pravir Kumar Gupta

IPC: G10L15/05 ,  G06F16/683 ,  G10L15/04 ,  G10L15/065 ,  G10L15/22 ,  G10L15/26 ,  G10L25/78

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing are described. In one aspect, a method includes the action of accessing voice query log data that includes voice queries spoken by a particular user. The actions further include based on the voice query log data that includes voice queries spoken by a particular user, determining a pause threshold from the voice query log data that includes voice queries spoken by the particular user. The actions further include receiving, from the particular user, an utterance. The actions further include determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold. The actions further include based on determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold, processing the utterance as a voice query.

公开(公告)号：US11062696B2

公开(公告)日：2021-07-13

申请号：US16377767

申请日：2019-04-08

Applicant: Google LLC

Inventor： Siddhi Tadpatrikar ,  Michael Buchanan ,  Pravir Kumar Gupta

IPC: G10L15/04 ,  G10L15/05 ,  G06F16/683 ,  G10L15/065 ,  G10L15/22 ,  G10L15/26 ,  G10L25/78 ,  G10L15/07

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing are described. In one aspect, a method includes the action of accessing voice query log data that includes voice queries spoken by a particular user. The actions further include based on the voice query log data that includes voice queries spoken by a particular user, determining a pause threshold from the voice query log data that includes voice queries spoken by the particular user. The actions further include receiving, from the particular user, an utterance. The actions further include determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold. The actions further include based on determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold, processing the utterance as a voice query.

公开(公告)号：US10339917B2

公开(公告)日：2019-07-02

申请号：US14844563

申请日：2015-09-03

Applicant: Google LLC

Inventor： Petar Aleksic ,  Glen Shires ,  Michael Buchanan

IPC: G10L15/04 ,  G10L15/18 ,  G10L15/22 ,  G06F17/27

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data including an utterance, obtaining context data that indicates one or more expected speech recognition results, determining an expected speech recognition result based on the context data, receiving an intermediate speech recognition result generated by a speech recognition engine, comparing the intermediate speech recognition result to the expected speech recognition result for the audio data based on the context data, determining whether the intermediate speech recognition result corresponds to the expected speech recognition result for the audio data based on the context data, and setting an end of speech condition and providing a final speech recognition result in response to determining the intermediate speech recognition result matches the expected speech recognition result, the final speech recognition result including the one or more expected speech recognition results indicated by the context data.

公开(公告)号：US10269341B2

公开(公告)日：2019-04-23

申请号：US15196663

申请日：2016-06-29

Applicant: Google LLC

Inventor： Siddhi Tadpatrikar ,  Michael Buchanan ,  Pravir Kumar Gupta

IPC: G10L15/26 ,  G10L15/05 ,  G10L25/78 ,  G10L15/065 ,  G06F17/30 ,  G10L15/04 ,  G10L15/22 ,  G10L15/07

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing are described. In one aspect, a method includes the action of accessing voice query log data that includes voice queries spoken by a particular user. The actions further include based on the voice query log data that includes voice queries spoken by a particular user, determining a pause threshold from the voice query log data that includes voice queries spoken by the particular user. The actions further include receiving, from the particular user, an utterance. The actions further include determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold. The actions further include based on determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold, processing the utterance as a voice query.

公开(公告)号：US20210248995A1

公开(公告)日：2021-08-12

申请号：US17245019

申请日：2021-04-30

Applicant: Google LLC

Inventor： Michael Buchanan ,  Pravir Kumar Gupta ,  Christopher Bo Tandiono

IPC: G10L15/05 ,  G10L17/06 ,  G10L15/04 ,  G10L15/22 ,  G10L15/26 ,  G10L25/87 ,  G10L25/51

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

公开(公告)号：US10546576B2

公开(公告)日：2020-01-28

申请号：US16154875

申请日：2018-10-09

Applicant: Google LLC

Inventor： Michael Buchanan ,  Pravir Kumar Gupta ,  Christopher Bo Tandiono

IPC: G10L17/00 ,  G10L15/05 ,  G10L17/06 ,  G10L15/04 ,  G10L15/22 ,  G10L15/26 ,  G10L25/87 ,  G10L25/51 ,  G10L25/78 ,  G10L25/90 ,  G10L15/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

公开(公告)号：US20190318721A1

公开(公告)日：2019-10-17

申请号：US16377767

申请日：2019-04-08

Applicant: Google LLC

Inventor： Siddhi Tadpatrikar ,  Michael Buchanan ,  Pravir Kumar Gupta

IPC: G10L15/05 ,  G10L15/065 ,  G10L15/22 ,  G06F16/683 ,  G10L15/26 ,  G10L25/78 ,  G10L15/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing are described. In one aspect, a method includes the action of accessing voice query log data that includes voice queries spoken by a particular user. The actions further include based on the voice query log data that includes voice queries spoken by a particular user, determining a pause threshold from the voice query log data that includes voice queries spoken by the particular user. The actions further include receiving, from the particular user, an utterance. The actions further include determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold. The actions further include based on determining that the particular user has stopped speaking for at least a period of time equal to the pause threshold, processing the utterance as a voice query.

公开(公告)号：US12051402B2

公开(公告)日：2024-07-30

申请号：US18189270

申请日：2023-03-24

Applicant: Google LLC

Inventor： Michael Buchanan ,  Pravir Kumar Gupta ,  Christopher Bo Tandiono

IPC: G10L15/05 ,  G10L15/04 ,  G10L15/22 ,  G10L15/26 ,  G10L17/06 ,  G10L25/51 ,  G10L25/87 ,  G10L15/08 ,  G10L25/78 ,  G10L25/90

CPC classification number: G10L15/05 ,  G10L15/04 ,  G10L15/22 ,  G10L15/26 ,  G10L17/06 ,  G10L25/51 ,  G10L25/87 ,  G10L2015/088 ,  G10L2015/223 ,  G10L25/78 ,  G10L2025/783 ,  G10L25/90

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

公开(公告)号：US11996085B2

公开(公告)日：2024-05-28

申请号：US17115403

申请日：2020-12-08

Applicant: Google LLC

Inventor： Petar Aleksic ,  Glen Shires ,  Michael Buchanan

IPC: G10L15/04 ,  G06F3/16 ,  G10L15/05 ,  G10L15/08 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26 ,  G10L25/78

CPC classification number: G10L15/05 ,  G06F3/167 ,  G10L15/04 ,  G10L15/1815 ,  G10L15/22 ,  G10L15/26 ,  G10L25/78 ,  G10L2015/088 ,  G10L2025/783

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data including an utterance, obtaining context data that indicates one or more expected speech recognition results, determining an expected speech recognition result based on the context data, receiving an intermediate speech recognition result generated by a speech recognition engine, comparing the intermediate speech recognition result to the expected speech recognition result for the audio data based on the context data, determining whether the intermediate speech recognition result corresponds to the expected speech recognition result for the audio data based on the context data, and setting an end of speech condition and providing a final speech recognition result in response to determining the intermediate speech recognition result matches the expected speech recognition result, the final speech recognition result including the one or more expected speech recognition results indicated by the context data.