利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.04 秒)

    Method of managing a speech cache
    1.
    发明授权
    Method of managing a speech cache 有权
    管理语音缓存的方法

    公开(公告)号：US06741963B1

    公开(公告)日：2004-05-25

    申请号：US09598603

    申请日：2000-06-21

    申请人： Daniel E. Badt ,  Peter J. Guasti ,  Gary R. Hanson ,  Amado Nassiff ,  Edwin A. Rodriguez ,  Harvey M. Ruback ,  Carl A. Smith ,  Ronald E. VanBuskirk ,  Huifang Wang ,  Steven G. Woodward

    发明人： Daniel E. Badt ,  Peter J. Guasti ,  Gary R. Hanson ,  Amado Nassiff ,  Edwin A. Rodriguez ,  Harvey M. Ruback ,  Carl A. Smith ,  Ronald E. VanBuskirk ,  Huifang Wang ,  Steven G. Woodward

    IPC分类号： G10L1500

    CPC分类号： G10L15/285 ,  G10L15/22

    摘要： A method and a system for improving recall of speech data in a computer speech system can include a plurality of speech cache management steps including providing a speech cache, receiving a speech system input and identifying a speech event in the received speech system input, the speech event comprising speech data. Subsequently, the speech data can be compared to pre-determined speech cache entry criteria; and, if the speech data meets one of the pre-determined entry criteria, at least one entry can be added to the speech cache, the at least one entry corresponding to the speech data. Additionally, the speech data can be compared to pre-determined speech cache exit criteria; and, if the speech data meets one of the pre-determined exit criteria, at least one entry can be purged from the speech cache, the at least one entry corresponding to the speech data. The entry criteria can include frequently used speech data, recently used speech data, and important speech data. Similarly, the exit criteria can include least frequently used speech data associated with each entry in the speech cache, least recently used speech data associated with each entry in the speech cache and least important speed data associated with each entry in the speech cache.

    摘要翻译： 一种用于改善计算机语音系统中的语音数据的回忆的方法和系统可以包括多个语音高速缓存管理步骤，包括提供语音高速缓存，接收语音系统输入和识别接收到的语音系统输入中的语音事件，语音 事件包括语音数据。 随后，语音数据可以与预定的语音高速缓存入口标准进行比较; 以及如果所述语音数据满足所述预定条目标准之一，则至少一个条目可以被添加到所述语音高速缓存，所述至少一个条目对应于所述语音数据。 另外，语音数据可以与预定语音高速缓存退出标准进行比较; 并且如果语音数据满足预定的退出准则之一，则可以从语音高速缓存中清除至少一个条目，该对应于该语音数据的至少一个条目。 入门标准可以包括经常使用的语音数据，最近使用的语音数据和重要的语音数据。 类似地，退出标准可以包括与语音高速缓存中的每个条目相关联的最少频繁使用的语音数据，与语音高速缓存中的每个条目相关联的最近最少使用的语音数据以及与语音高速缓存中的每个条目相关联的最小重要速度数据。

    Overriding default speech processing behavior using a default focus receiver
    5.
    发明授权
    Overriding default speech processing behavior using a default focus receiver 有权
    使用默认焦点接收器覆盖默认语音处理行为

    公开(公告)号：US07848928B2

    公开(公告)日：2010-12-07

    申请号：US11201003

    申请日：2005-08-10

    申请人： Lisa Abbott ,  Daniel E. Badt ,  John W. Eckhart ,  Harvey M. Ruback ,  Steven G. Woodward

    发明人： Lisa Abbott ,  Daniel E. Badt ,  John W. Eckhart ,  Harvey M. Ruback ,  Steven G. Woodward

    IPC分类号： G10L20/00

    CPC分类号： G10L15/28

    摘要： A method for implementing speech focus in a speech processing system can include the step of establishing a default focus receiver as a first entity to request speech focus of a speech processing system having multiple applications that share speech resources based upon speech focus. An event occurrence can be detected. An event handler of the default speech receiver can previously define behavior for the event occurrence and where default system behavior can be implemented within the speech processing system for the event occurrence. The default system behavior can be utilized when speech focus is not assigned during the event occurrence. Responsive to the event occurrence, at least one programmatic action can be performed in accordance with machine readable instructions of the event handler. The default system behavior is not implemented responsive to the event occurrence.

    摘要翻译： 用于在语音处理系统中实现语音焦点的方法可以包括建立默认焦点接收机作为第一实体的步骤，以基于语音焦点来共享具有共享语音资源的多个应用的​​语音处理系统的语音焦点。 可以检测到事件发生。 默认语音接收器的事件处理程序可以预先定义事件发生的行为，并且在事件发生的语音处理系统内可以实现默认系统行为。 在事件发生期间未分配语音焦点时，可以使用默认系统行为。 响应于事件发生，可以根据事件处理程序的机器可读指令执行至少一个编程动作。 默认系统行为不能响应于事件发生而实现。

    Enhancement to Viterbi speech processing algorithm for hybrid speech models that conserves memory
    6.
    发明授权
    Enhancement to Viterbi speech processing algorithm for hybrid speech models that conserves memory 有权
    增强维特比语音处理算法，用于保存记忆的混合语音模型

    公开(公告)号：US07805305B2

    公开(公告)日：2010-09-28

    申请号：US11548976

    申请日：2006-10-12

    申请人： Daniel E. Badt ,  Tomas Beran ,  Radek Hampl ,  Pavel Krbec ,  Jan Sedivy

    发明人： Daniel E. Badt ,  Tomas Beran ,  Radek Hampl ,  Pavel Krbec ,  Jan Sedivy

    IPC分类号： G10L15/18

    CPC分类号： G10L15/12 ,  G10L15/197

    摘要： The present invention discloses a method for semantically processing speech for speech recognition purposes. The method can reduce an amount of memory required for a Viterbi search of an N-gram language model having a value of N greater than two and also having at least one embedded grammar that appears in a multiple contexts to a memory size of approximately a bigram model search space with respect to the embedded grammar. The method also reduces needed CPU requirements. Achieved reductions can be accomplished by representing the embedded grammar as a recursive transition network (RTN), where only one instance of the recursive transition network is used for the contexts. Other than the embedded grammars, a Hidden Markov Model (HMM) strategy can be used for the search space.

    摘要翻译： 本发明公开了一种用于语音处理语音以进行语音识别的方法。 该方法可以减少具有N大于2的N语言模型的维特比搜索所需的存储器量，并且还具有出现在多个上下文中的至少一个嵌入式语法到大约二进制的存储器大小 关于嵌入式语法的模型搜索空间。 该方法还可以减少所需的CPU需求。 通过将嵌入式语法表示为递归转换网络（RTN）可以实现实现的减少，其中只有递归过渡网络的一个实例用于上下文。 除了嵌入式语法之外，隐藏马尔可夫模型（HMM）策略可用于搜索空间。

    Providing speech recognition data to a speech enabled device when providing a new entry that is selectable via a speech recognition interface of the device
    7.
    发明授权
    Providing speech recognition data to a speech enabled device when providing a new entry that is selectable via a speech recognition interface of the device 有权
    当提供可经由设备的语音识别接口选择的新条目时，将语音识别数据提供给支持语音的设备

    公开(公告)号：US08010345B2

    公开(公告)日：2011-08-30

    申请号：US11958713

    申请日：2007-12-18

    申请人： Neal J. Alewine ,  Daniel E. Badt

    发明人： Neal J. Alewine ,  Daniel E. Badt

    IPC分类号： G10L19/00

    CPC分类号： G10L15/183 ,  G10L15/06

    摘要： The present invention discloses a solution for providing a phonetic representation for a content item along with a content item delivered to a speech enabled computing device. The phonetic representation can be specified in a manner that enables it to be added to a speech recognition grammar of the speech enabled computing device. Thus, the device can recognize speech commands using the newly added phonetic representation that involve the content item. Current implementations of speech recognition systems of this type rely internal generation of speech recognition data that is added to the speech recognition grammar. Generation of speech recognition data can, however, be resource intensive, which can be particularly problematic when the speech enabled device is resource limited. The disclosed solution offloads the task of providing the speech recognition data to an external device, such as a relatively resource rich server or a desktop device.

    摘要翻译： 本发明公开了一种用于为内容项目提供语音表示以及递送到支持语音的计算设备的内容项目的解决方案。 可以以使其能够被添加到支持语音的计算设备的语音识别语法的方式来指定语音表示。 因此，设备可以使用涉及内容项的新添加的语音表示来识别语音命令。 这种类型的语音识别系统的当前实现依赖于加入到语音识别语法中的语音识别数据的内部生成。 然而，语音识别数据的生成可以是资源密集型的，当语音使能设备被资源限制时，这可能是特别有问题的。 所公开的解决方案将提供语音识别数据的任务卸载到诸如相对资源丰富的服务器或桌面设备的外部设备。

    ENHANCEMENT TO VITERBI SPEECH PROCESSING ALGORITHM FOR HYBRID SPEECH MODELS THAT CONSERVES MEMORY
    8.
    发明申请
    ENHANCEMENT TO VITERBI SPEECH PROCESSING ALGORITHM FOR HYBRID SPEECH MODELS THAT CONSERVES MEMORY 有权
    对于保留记忆的混合语音模型的VITERBI语音处理算法的增强

    公开(公告)号：US20080091429A1

    公开(公告)日：2008-04-17

    申请号：US11548976

    申请日：2006-10-12

    申请人： Daniel E. Badt ,  Tomas Beran ,  Radek Hampl ,  Pavel Krbec ,  Jan Sedivy

    发明人： Daniel E. Badt ,  Tomas Beran ,  Radek Hampl ,  Pavel Krbec ,  Jan Sedivy

    IPC分类号： G10L15/28

    CPC分类号： G10L15/12 ,  G10L15/197

    摘要： The present invention discloses a method for semantically processing speech for speech recognition purposes. The method can reduce an amount of memory required for a Viterbi search of an N-gram language model having a value of N greater than two and also having at least one embedded grammar that appears in a multiple contexts to a memory size of approximately a bigram model search space with respect to the embedded grammar. The method also reduces needed CPU requirements. Achieved reductions can be accomplished by representing the embedded grammar as a recursive transition network (RTN), where only one instance of the recursive transition network is used for the contexts. Other than the embedded grammars, a Hidden Markov Model (HMM) strategy can be used for the search space.

    摘要翻译： 本发明公开了一种用于语音处理语音以进行语音识别的方法。 该方法可以减少具有N大于2的N-gram语言模型的Viterbi搜索所需的存储器量，并且还具有出现在多个上下文中的至少一个嵌入语法到大约二进制的存储器大小 关于嵌入式语法的模型搜索空间。 该方法还可以减少所需的CPU需求。 通过将嵌入式语法表示为递归转换网络（RTN）可以实现实现的减少，其中只有递归过渡网络的一个实例用于上下文。 除了嵌入式语法之外，隐藏马尔可夫模型（HMM）策略可用于搜索空间。