System and method for tuning and testing in a speech recognition system
    1.
    发明授权
    System and method for tuning and testing in a speech recognition system 有权
    用于语音识别系统中调谐和测试的系统和方法

    公开(公告)号:US07962331B2

    公开(公告)日:2011-06-14

    申请号:US12255564

    申请日:2008-10-21

    IPC分类号: G10L11/06

    摘要: Systems and methods for improving the performance of a speech recognition system. In some embodiments a tuner module and/or a tester module are configured to cooperate with a speech recognition system. The tester and tuner modules can be configured to cooperate with each other. In one embodiment, the tuner module may include a module for playing back a selected portion of a digital data audio file, a module for creating and/or editing a transcript of the selected portion, and/or a module for displaying information associated with a decoding of the selected portion, the decoding generated by a speech recognition engine. In other embodiments, the tester module can include an editor for creating and/or modifying a grammar, a module for receiving a selected portion of a digital audio file and its corresponding transcript, and a scoring module for producing scoring statistics of the decoding based at least in part on the transcript.

    摘要翻译: 用于提高语音识别系统性能的系统和方法。 在一些实施例中,调谐器模块和/或测试器模块被配置为与语音识别系统协作。 测试器和调谐器模块可以配置为相互配合。 在一个实施例中,调谐器模块可以包括用于回放数字数据音频文件的所选部分的模块,用于创建和/或编辑所选部分的抄本的模块,和/或用于显示与所选择的部分相关联的信息的模块 解码所选择的部分,由语音识别引擎产生的解码。 在其他实施例中,测试器模块可以包括用于创建和/或修改语法的编辑器,用于接收数字音频文件的选定部分的模块及其对应的抄本,以及用于产生基于以下内容的解码的评分统计的评分模块: 至少部分在抄本上。

    SYSTEM AND METHOD FOR TUNING AND TESTING IN A SPEECH RECOGNITION SYSTEM
    2.
    发明申请
    SYSTEM AND METHOD FOR TUNING AND TESTING IN A SPEECH RECOGNITION SYSTEM 有权
    用于在语音识别系统中进行调谐和测试的系统和方法

    公开(公告)号:US20090043576A1

    公开(公告)日:2009-02-12

    申请号:US12255564

    申请日:2008-10-21

    IPC分类号: G10L15/06

    摘要: Systems and methods for improving the performance of a speech recognition system. In some embodiments a tuner module and/or a tester module are configured to cooperate with a speech recognition system. The tester and tuner modules can be configured to cooperate with each other. In one embodiment, the tuner module may include a module for playing back a selected portion of a digital data audio file, a module for creating and/or editing a transcript of the selected portion, and/or a module for displaying information associated with a decoding of the selected portion, the decoding generated by a speech recognition engine. In other embodiments, the tester module can include an editor for creating and/or modifying a grammar, a module for receiving a selected portion of a digital audio file and its corresponding transcript, and a scoring module for producing scoring statistics of the decoding based at least in part on the transcript.

    摘要翻译: 用于提高语音识别系统性能的系统和方法。 在一些实施例中,调谐器模块和/或测试器模块被配置为与语音识别系统协作。 测试器和调谐器模块可以配置为相互配合。 在一个实施例中,调谐器模块可以包括用于回放数字数据音频文件的所选部分的模块,用于创建和/或编辑所选部分的抄本的模块,和/或用于显示与所选择的部分相关联的信息的模块 解码所选择的部分,由语音识别引擎产生的解码。 在其他实施例中,测试器模块可以包括用于创建和/或修改语法的编辑器,用于接收数字音频文件的选定部分的模块及其对应的抄本,以及用于产生基于以下内容的解码的评分统计的评分模块: 至少部分在抄本上。

    System and method for tuning and testing in a speech recognition system
    3.
    发明授权
    System and method for tuning and testing in a speech recognition system 有权
    用于语音识别系统中调谐和测试的系统和方法

    公开(公告)号:US07440895B1

    公开(公告)日:2008-10-21

    申请号:US10725281

    申请日:2003-12-01

    IPC分类号: G10L15/06

    摘要: Systems and methods for improving the performance of a speech recognition system. In some embodiments a tuner module and/or a tester module are configured to cooperate with a speech recognition system. The tester and tuner modules can be configured to cooperate with each other. In one embodiment, the tuner module may include a module for playing back a selected portion of a digital data audio file, a module for creating and/or editing a transcript of the selected portion, and/or a module for displaying information associated with a decoding of the selected portion, the decoding generated by a speech recognition engine. In other embodiments, the tester module can include an editor for creating and/or modifying a grammar, a module for receiving a selected portion of a digital audio file and its corresponding transcript, and a scoring module for producing scoring statistics of the decoding based at least in part on the transcript.

    摘要翻译: 用于提高语音识别系统性能的系统和方法。 在一些实施例中,调谐器模块和/或测试器模块被配置为与语音识别系统协作。 测试器和调谐器模块可以配置为相互配合。 在一个实施例中,调谐器模块可以包括用于回放数字数据音频文件的所选部分的模块,用于创建和/或编辑所选部分的抄本的模块,和/或用于显示与所选择的部分相关联的信息的模块 解码所选择的部分,由语音识别引擎产生的解码。 在其他实施例中,测试器模块可以包括用于创建和/或修改语法的编辑器,用于接收数字音频文件的选定部分的模块及其对应的抄本,以及用于产生基于以下内容的解码的评分统计的评分模块: 至少部分在抄本上。

    Speech recognition concept confidence measurement
    4.
    发明授权
    Speech recognition concept confidence measurement 有权
    语音识别概念置信度测量

    公开(公告)号:US07324940B1

    公开(公告)日:2008-01-29

    申请号:US10789389

    申请日:2004-02-27

    IPC分类号: G10L15/00

    CPC分类号: G10L15/10

    摘要: Systems and methods for determining a confidence score associated with a decoding output of a speech recognition engine. In one embodiment, a method of determining the confidence score comprises arranging time frame and acoustic score data into an array, determining a phoneme sequence in the array that yields the highest sum of acoustic scores under certain constraints, e.g., minimum number of time frames and order of phonemes in a phoneme string. A relative score is derived by applying a functional relationship between the acoustic score and different sums comprising acoustic scores from the array. The confidence score, in some embodiments, depends at least in part on the relative score and a measure of ambiguity associated with similar sounding phrases being included in different concepts of a specified grammar.

    摘要翻译: 用于确定与语音识别引擎的解码输出相关联的置信度得分的系统和方法。 在一个实施例中,确定置信度分数的方法包括将时间帧和声学分数数据布置到阵列中,确定阵列中的音素序列,其在某些约束下产生最高的声分数和,例如最小时间帧数, 音素字串中的音素顺序。 通过在声分数和包括来自阵列的声分数的不同和之间应用功能关系来导出相对得分。 在一些实施例中,置信度得分至少部分地依赖于相对分数和与包括在指定语法的不同概念中的类似的声音短语相关联的模糊度的度量。

    Call flow object model in a speech recognition system
    5.
    发明授权
    Call flow object model in a speech recognition system 有权
    在语音识别系统中调用流对象模型

    公开(公告)号:US07877261B1

    公开(公告)日:2011-01-25

    申请号:US12103509

    申请日:2008-04-15

    IPC分类号: G10L15/00

    CPC分类号: G10L15/22 G10L2015/228

    摘要: Systems and methods are provided for embodiments of a speech recognition system call flow object model. The systems and methods organize and execute, for example, multiple question directed dialogs, overview dialogs, or natural language directed dialogs. In certain embodiments, the organizing and executing of the natural language directed dialogs uses primary and secondary concepts without requiring a structured response. The systems and methods enable the call flow designers to define particular call flows without requiring the designers to perform any programming or coding.

    摘要翻译: 提供了用于语音识别系统呼叫流对象模型的实施例的系统和方法。 系统和方法组织和执行,例如,多个问题引导的对话框,概述对话框或自然语言导向的对话框。 在某些实施例中,自然语言定向对话的组织和执行使用主要和次要概念,而不需要结构化的响应。 系统和方法使得呼叫流设计者可以定义特定的呼叫流,而不需要设计者执行任何编程或编码。

    Call flow object model in a speech recognition system
    6.
    发明授权
    Call flow object model in a speech recognition system 有权
    在语音识别系统中调用流对象模型

    公开(公告)号:US07359860B1

    公开(公告)日:2008-04-15

    申请号:US10789397

    申请日:2004-02-27

    IPC分类号: G10L15/00

    CPC分类号: G10L15/22 G10L2015/228

    摘要: Systems and methods are provided for embodiments of a speech recognition system call flow object model. The systems and methods organize and execute, for example, multiple question directed dialogs, overview dialogs, or natural language directed dialogs. In certain embodiments, the organizing and executing of the natural language directed dialogs uses primary and secondary concepts without requiring a structured response. The systems and methods enable the call flow designers to define particular call flows without requiring the designers to perform any programming or coding.

    摘要翻译: 提供了用于语音识别系统呼叫流对象模型的实施例的系统和方法。 系统和方法组织和执行,例如,多个问题引导的对话框,概述对话框或自然语言导向的对话框。 在某些实施例中,自然语言定向对话的组织和执行使用主要和次要概念,而不需要结构化的响应。 系统和方法使得呼叫流设计者可以定义特定的呼叫流,而不需要设计者执行任何编程或编码。