公开(公告)号：US09378731B2

公开(公告)日：2016-06-28

申请号：US14693268

申请日：2015-04-22

Applicant: Google Inc.

Inventor： Olga Kapralova ,  John Paul Alex ,  Eugene Weinstein ,  Pedro J. Moreno Mengibar ,  Olivier Siohan ,  Ignacio Lopez Moreno

IPC: G10L15/00 ,  G10L15/06 ,  G10L25/30 ,  G10L15/187 ,  G10L15/26

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/16 ,  G10L15/187 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/0633

Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

Abstract translation: 本公开涉及训练语音识别系统。 一个示例性方法包括接收语音数据项集合，其中每个语音数据项对应于先前由生产语音识别器提交用于转录的话语。 生产语音识别器使用初始生产语音识别器组件来产生语音数据项的转录。 使用离线语音识别器生成每个语音数据项的转录，并且将离线语音识别器组件配置为与初始制作语音识别器组件相比提高语音识别精度。 使用由离线语音识别器生成的语音数据项的转录的所选择的子集来对生产语音识别器进行更新的制作语音识别器组件的训练。 更新的生产语音识别器组件被提供给生产语音识别器，用于转录随后接收的语音数据项。

公开(公告)号：US20160267903A1

公开(公告)日：2016-09-15

申请号：US15164263

申请日：2016-05-25

Applicant: Google Inc.

Inventor： Olga Kapralova ,  John Paul Alex ,  Eugene Weinstein ,  Pedro J. Moreno Mengibar ,  Olivier Siohan ,  Ignacio Lopez Moreno

IPC: G10L15/06 ,  G10L15/01 ,  G10L15/16 ,  G10L15/30

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/16 ,  G10L15/187 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/0633

Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

公开(公告)号：US20160093294A1

公开(公告)日：2016-03-31

申请号：US14693268

申请日：2015-04-22

Applicant: Google Inc.

Inventor： Olga Kapralova ,  John Paul Alex ,  Eugene Weinstein ,  Pedro J. Moreno Mengibar ,  Olivier Siohan ,  Ignacio Lopez Moreno

IPC: G10L15/06 ,  G10L15/187 ,  G10L15/26 ,  G10L25/30

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/16 ,  G10L15/187 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/0633

Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

Abstract translation: 本公开涉及训练语音识别系统。 一个示例性方法包括接收语音数据项集合，其中每个语音数据项对应于先前由生产语音识别器提交用于转录的话语。 生产语音识别器使用初始生产语音识别器组件来产生语音数据项的转录。 使用离线语音识别器生成每个语音数据项的转录，并且将离线语音识别器组件配置为与初始制作语音识别器组件相比提高语音识别精度。 使用由离线语音识别器生成的语音数据项的转录的所选择的子集来对生产语音识别器进行更新的制作语音识别器组件的训练。 更新的生产语音识别器组件被提供给生产语音识别器，用于转录随后接收的语音数据项。

公开(公告)号：US20180033426A1

公开(公告)日：2018-02-01

申请号：US15224104

申请日：2016-07-29

Applicant: Google Inc.

Inventor： Olga Kapralova ,  Evgeny A. Cherepanov ,  Dmitry Osmakov ,  Martin Baeuml ,  Gleb Skobeltsyn

IPC: G10L15/06 ,  G10L15/10 ,  G10L15/01

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/06 ,  G10L15/10 ,  G10L15/22 ,  G10L15/32 ,  G10L2015/0635 ,  G10L2015/0638

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.

公开(公告)号：US09472187B2

公开(公告)日：2016-10-18

申请号：US15164263

申请日：2016-05-25

Applicant: Google Inc.

Inventor： Olga Kapralova ,  John Paul Alex ,  Eugene Weinstein ,  Pedro J. Moreno Mengibar ,  Olivier Siohan ,  Ignacio Lopez Moreno

IPC: G10L15/06 ,  G10L15/30 ,  G10L15/01 ,  G10L15/16

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/16 ,  G10L15/187 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/0633

Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.