Subword unit posterior probability for measuring confidence
    1.
    发明授权
    Subword unit posterior probability for measuring confidence 有权
    子字单位后验概率用于测量置信度

    公开(公告)号:US07890325B2

    公开(公告)日:2011-02-15

    申请号:US11376803

    申请日:2006-03-16

    IPC分类号: G06F17/27 G10L15/00 G10L15/28

    摘要: Speech recognition such as command and control speech recognition generally use a context free grammar to constrain the decoding process. Word or subword background model are constructed to repopulate dynamic hypothesis space, especially when word spareness is at issue. The background models can be later used in speech recognition. During speech recognition, background and conventional context free grammar decoding are used to measure confidence. The discussion above is merely provided for general background information and is not intended to be used as an aid in determining the scope of the claimed subject matter.

    摘要翻译: 诸如命令和控制语音识别之类的语音识别通常使用无上下文的语法来限制解码过程。 构建词或子词背景模型,以重新构建动态假设空间,特别是在词语空间问题时。 背景模型可以稍后用于语音识别。 在语音识别期间,使用背景和常规上下文无关语法解码来测量置信度。 上面的讨论仅用于一般背景信息,并不旨在用于帮助确定所要求保护的主题的范围。

    Calculating cost measures between HMM acoustic models
    2.
    发明申请
    Calculating cost measures between HMM acoustic models 有权
    计算HMM声学模型之间的成本测量

    公开(公告)号:US20080059184A1

    公开(公告)日:2008-03-06

    申请号:US11507859

    申请日:2006-08-22

    IPC分类号: G10L15/14

    CPC分类号: G10L15/142

    摘要: Measurement of Kullback-Leibler Divergence (KLD) between hidden Markov models (HMM) of acoustic units utilizes an unscented transform to approximate KLD between Gaussian mixtures. Dynamic programming equalizes the number of states between HMMs having a different number of states, while the total KLD of the HMMs is obtained by summing individual KLDs calculated by state pair by state pair comparisons.

    摘要翻译: 声学单元的隐马尔可夫模型(HMM)之间的Kullback-Leibler发散(KLD)的测量利用无差异变换来近似高斯混合之间的KLD。 动态规划使具有不同数量状态的HMM之间的状态数量相等,而HMM的总KLD是通过将通过状态对比较的状态对计算的各个KLD求和来获得的。

    Calculating cost measures between HMM acoustic models
    3.
    发明授权
    Calculating cost measures between HMM acoustic models 有权
    计算HMM声学模型之间的成本测量

    公开(公告)号:US08234116B2

    公开(公告)日:2012-07-31

    申请号:US11507859

    申请日:2006-08-22

    IPC分类号: G10L15/14 G10L15/10 G10L15/28

    CPC分类号: G10L15/142

    摘要: Measurement of Kullback-Leibler Divergence (KLD) between hidden Markov models (HMM) of acoustic units utilizes an unscented transform to approximate KLD between Gaussian mixtures. Dynamic programming equalizes the number of states between HMMs having a different number of states, while the total KLD of the HMMs is obtained by summing individual KLDs calculated by state pair by state pair comparisons.

    摘要翻译: 声学单元的隐马尔可夫模型(HMM)之间的Kullback-Leibler发散(KLD)的测量利用无差异变换来近似高斯混合之间的KLD。 动态规划使具有不同数量状态的HMM之间的状态数量相等,而HMM的总KLD是通过将通过状态对比较的状态对计算的各个KLD求和来获得的。

    EVENT RECOGNITION
    5.
    发明申请
    EVENT RECOGNITION 审中-公开
    活动认可

    公开(公告)号:US20080215318A1

    公开(公告)日:2008-09-04

    申请号:US11680827

    申请日:2007-03-01

    IPC分类号: G10L15/00

    CPC分类号: G10L17/26 G10L25/48

    摘要: Recognition of events can be performed by accessing an audio signal having static and dynamic features. A value for the audio signal can be calculated by utilizing different weights for the static and dynamic features such that a frame of the audio signal can be associated with a particular event. A filter can also be used to aid in determining the event for the frame.

    摘要翻译: 可以通过访问具有静态和动态特征的音频信号来执行对事件的识别。 可以通过利用静态和动态特征的不同权重来计算音频信号的值,使得音频信号的帧可以与特定事件相关联。 也可以使用滤波器来帮助确定帧的事件。