公开(公告)号：US11587558B2

公开(公告)日：2023-02-21

申请号：US16988292

申请日：2020-08-07

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/06 ,  G10L15/187 ,  G06F16/9535 ,  G06Q30/02 ,  G10L17/26 ,  G10L15/18 ,  G10L15/22 ,  G10L15/02 ,  G10L15/14 ,  G06F16/95

Abstract: A computer-implemented method includes generating an empirically derived acoustic confusability measure by processing example utterances and iterating from an initial estimate of the acoustic confusability measure to improve the measure. The method can further include using the acoustic confusability measure to selectively limit phrases to make recognizable by a speech recognition application.

公开(公告)号：US20200372903A1

公开(公告)日：2020-11-26

申请号：US16988292

申请日：2020-08-07

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/187 ,  G06F16/9535 ,  G06Q30/02 ,  G10L17/26 ,  G10L15/18 ,  G10L15/22 ,  G10L15/02 ,  G10L15/14

Abstract: A computer-implemented method includes generating an empirically derived acoustic confusability measure by processing example utterances and iterating from an initial estimate of the acoustic confusability measure to improve the measure. The method can further include using the acoustic confusability measure to selectively limit phrases to make recognizable by a speech recognition application.

公开(公告)号：US09305549B2

公开(公告)日：2016-04-05

申请号：US14513093

申请日：2014-10-13

Applicant: PROMPTU SYSTEMS CORPORATION

Inventor： Joseph Bruce Stampleman ,  Harry Printz

IPC: G10L15/00 ,  G10L15/22 ,  G06Q30/02 ,  G10L17/26 ,  G10L15/18 ,  G06F17/30

CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: A method and apparatus to identify names, personalities, titles, and topics that are present in a repository and to identify names, personalities, titles, and topics that are not present in the repository, uses information from external data sources, notably the text used in non-speech, text-based searches, to expand the search terms. The expansion takes place in two forms: (1) finding plausible linguistic variants of existing search terms that are already comprehended in the repository, but that are present under slightly different names; and (2) expanding the existing search term list with items that should be there by virtue of their currency in popular culture, but which for whatever reason have not yet been reflected with content items in the repository.

Abstract translation: 识别存储库中存在的名称，个性，标题和主题以及识别存储库中不存在的名称，个性，标题和主题的方法和装置使用来自外部数据源的信息，特别是所使用的文本 在非语音，基于文本的搜索中，扩展搜索词。 扩展有两种形式：（1）找到已经在知识库中理解的现有搜索词的合理语言变体，但存在于稍微不同的名称下; 和（2）扩大现有的搜索项目列表，其项目应该是以流通文化中的货币存在的，但由于任何原因，还没有反映在存储库中的内容项目。

公开(公告)号：US20190051294A1

公开(公告)日：2019-02-14

申请号：US16158900

申请日：2018-10-12

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/187 ,  G10L15/14

CPC classification number: G10L15/187 ,  G06F16/95 ,  G06F16/9535 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

公开(公告)号：US10121469B2

公开(公告)日：2018-11-06

申请号：US15457964

申请日：2017-03-13

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/187 ,  G10L15/02 ,  G10L15/14

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

公开(公告)号：US10748527B2

公开(公告)日：2020-08-18

申请号：US16158900

申请日：2018-10-12

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/187 ,  G06F16/9535 ,  G06Q30/02 ,  G10L17/26 ,  G10L15/18 ,  G10L15/22 ,  G10L15/02 ,  G10L15/14 ,  G06F16/95

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

公开(公告)号：US20170186421A1

公开(公告)日：2017-06-29

申请号：US15457964

申请日：2017-03-13

Applicant: Promptu Systems Corporation

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/187 ,  G10L15/14 ,  G10L15/02

CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

公开(公告)号：US09626965B2

公开(公告)日：2017-04-18

申请号：US14574314

申请日：2014-12-17

Applicant: PROMPTU SYSTEMS CORPORATION

Inventor： Harry Printz ,  Naren Chittar

IPC: G10L15/12 ,  G10L15/187 ,  G10L15/22 ,  G06Q30/02 ,  G10L17/26 ,  G10L15/18 ,  G06F17/30

CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

公开(公告)号：US20150106100A1

公开(公告)日：2015-04-16

申请号：US14574314

申请日：2014-12-17

Applicant: PROMPTU SYSTEMS CORPORATION

Inventor： Harry Printz ,  Naren CHITTAR

IPC: G10L15/22 ,  G10L15/18

CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

Abstract translation: 声学混淆度测量的有效经验确定，计算和使用包括：（1）经验导出的声学混淆度量度，包括用于确定给定语言中的任何两个文本短语之间的声学​​混淆性的装置，其中声学混淆度的度量是 经验地衍生自应用特定语音识别技术的示例，其中该过程不需要访问语音识别技术的内部计算模型，并且不依赖于任何特定的内部结构或建模技术，并且其中过程是 基于初步估计的迭代改进; （2）用于有效计算经验导出的声学混淆度测量的技术，包括有效应用声学混淆评分的手段，允许实际应用于非常大规模的问题; 和（3）使用声学混淆度量的方法，对哪些特定短语进行原则性的选择，使语音识别应用程序可识别。

公开(公告)号：US08862596B2

公开(公告)日：2014-10-14

申请号：US13667446

申请日：2012-11-02

Applicant: Promptu Systems Corporation

Inventor： Joseph Bruce Stampleman ,  Harry Printz

IPC: G06F17/30 ,  G10L17/26 ,  G06Q30/02

CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

Abstract: A method and apparatus to identify names, personalities, titles, and topics that are present in a repository and to identify names, personalities, titles, and topics that are not present in the repository, uses information from external data sources, notably the text used in non-speech, text-based searches, to expand the search terms. The expansion takes place in two forms: (1) finding plausible linguistic variants of existing search terms that are already comprehended in the repository, but that are present under slightly different names; and (2) expanding the existing search term list with items that should be there by virtue of their currency in popular culture, but which for whatever reason have not yet been reflected with content items in the repository.

Abstract translation: 识别存储库中存在的名称，个性，标题和主题以及识别存储库中不存在的名称，个性，标题和主题的方法和装置使用来自外部数据源的信息，特别是所使用的文本 在非语音，基于文本的搜索中，扩展搜索词。 扩展有两种形式：（1）找到已经在知识库中理解的现有搜索词的合理语言变体，但存在于稍微不同的名称下; 和（2）扩大现有的搜索项目列表，其项目应该是以流通文化中的货币存在的，但由于任何原因，还没有反映在存储库中的内容项目。