公开(公告)号：US08285542B2

公开(公告)日：2012-10-09

申请号：US13027921

申请日：2011-02-15

申请人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

发明人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

IPC分类号： G06F17/21

CPC分类号： G10L15/063 ,  G10L15/197

摘要： A statistical language model is trained for use in a directory assistance system using the data in a directory assistance listing corpus. Calculations are made to determine how important words in the corpus are in distinguishing a listing from other listings, and how likely words are to be omitted or added by a user. The language model is trained using these calculations.

摘要翻译： 训练统计语言模型，以使用目录援助列表语料库中的数据在目录辅助系统中使用。 进行计算，以确定语料库中的单词在区分列表和其他列表中的重要程度以及用户可能忽略或添加单词的可能性。 使用这些计算训练语言模型。

公开(公告)号：US08214215B2

公开(公告)日：2012-07-03

申请号：US12236530

申请日：2008-09-24

申请人： Jinyu Li ,  Li Deng ,  Dong Yu ,  Yifan Gong ,  Alejandro Acero

发明人： Jinyu Li ,  Li Deng ,  Dong Yu ,  Yifan Gong ,  Alejandro Acero

IPC分类号： G10L15/14

CPC分类号： G10L15/065 ,  G10L15/20

摘要： A speech recognition system described herein includes a receiver component that receives a distorted speech utterance. The speech recognition also includes an updater component that is in communication with a first model and a second model, wherein the updater component automatically updates parameters of the second model based at least in part upon joint estimates of additive and convolutive distortions output by the first model, wherein the joint estimates of additive and convolutive distortions are estimates of distortions based on a phase-sensitive model in the speech utterance received by the receiver component. Further, distortions other than additive and convolutive distortions, including other stationary and nonstationary sources, can also be estimated used to update the parameters of the second model.

摘要翻译： 本文描述的语音识别系统包括接收失真的语音话语的接收机组件。 所述语音识别还包括与第一模型和第二模型通信的更新器组件，其中所述更新器组件至少部分地基于由所述第一模型输出的加法和卷积失真的联合估计来自动更新所述第二模型的参数 其中，加法和卷积失真的联合估计是基于由接收器部件接收的语音发声中的相敏模型的失真估计。 此外，还可以估计用于更新第二模型参数的除加法和卷积失真之外的失真，包括其他静止和非平稳源。

公开(公告)号：US08160878B2

公开(公告)日：2012-04-17

申请号：US12211114

申请日：2008-09-16

申请人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

IPC分类号： G10L15/14 ,  G10L15/20

CPC分类号： G10L15/144

摘要： A speech recognition system uses Gaussian mixture variable-parameter hidden Markov models (VPHMMs) to recognize speech under many different conditions. Each Gaussian mixture component of the VPHMMs is characterized by a mean parameter μ and a variance parameter Σ. Each of these Gaussian parameters varies as a function of at least one environmental conditioning parameter, such as, but not limited to, instantaneous signal-to-noise-ratio (SNR). The way in which a Gaussian parameter varies with the environmental conditioning parameter(s) can be approximated as a piecewise function, such as a cubic spline function. Further, the recognition system formulates the mean parameter μ and the variance parameter Σ of each Gaussian mixture component in an efficient form that accommodates the use of discriminative training and parameter sharing. Parameter sharing is carried out so that the otherwise very large number of parameters in the VPHMMs can be effectively reduced with practically feasible amounts of training data.

摘要翻译： 语音识别系统使用高斯混合可变参数隐马尔可夫模型（VPHMM）来识别许多不同条件下的语音。 VPHMM的每个高斯混合分量的特征在于平均参数μ和方差参数＆Sgr。 这些高斯参数中的每一个作为至少一个环境调节参数的函数而变化，例如但不限于瞬时信噪比（SNR）。 高斯参数随环境条件参数变化的方式可以近似为分段函数，如三次样条函数。 此外，识别系统制定均值参数μ和方差参数＆Sgr; 每个高斯混合分量以有效的形式适应使用歧视性训练和参数共享。 执行参数共享，以便通过实际可行的训练数据量可以有效地减少VPHMM中非常大量的参数。

公开(公告)号：US08145488B2

公开(公告)日：2012-03-27

申请号：US12211115

申请日：2008-09-16

申请人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

IPC分类号： G10L15/14

CPC分类号： G10L15/142

摘要： A speech recognition system uses Gaussian mixture variable-parameter hidden Markov models (VPHMMs) to recognize speech. The VPHMMs include Gaussian parameters that vary as a function of at least one environmental conditioning parameter. The relationship of each Gaussian parameter to the environmental conditioning parameter(s) is modeled using a piecewise fitting approach, such as by using spline functions. In a training phase, the recognition system can use clustering to identify classes of spline functions, each class grouping together spline functions which are similar to each other based on some distance measure. The recognition system can then store sets of spline parameters that represent respective classes of spline functions. An instance of a spline function that belongs to a class can make reference to an associated shared set of spline parameters. The Gaussian parameters can be represented in an efficient form that accommodates the use of sharing in the above-summarized manner.

摘要翻译： 语音识别系统使用高斯混合可变参数隐马尔可夫模型（VPHMM）来识别语音。 VPHMM包括作为至少一个环境调节参数的函数而变化的高斯参数。 每个高斯参数与环境条件参数的关系使用分段拟合方法建模，例如通过使用样条函数。 在训练阶段，识别系统可以使用聚类来识别样条函数的类别，每个类别根据一些距离度量将彼此相似的样条函数分组在一起。 识别系统然后可以存储表示各种样条函数的样条参数集合。 属于类的样条函数的一个实例可以引用相关联的一组样条参数。 高斯参数可以以适合以上述方式共享使用的有效形式来表示。

公开(公告)号：US08099279B2

公开(公告)日：2012-01-17

申请号：US11054301

申请日：2005-02-09

申请人： Alejandro Acero ,  Dong Yu

发明人： Alejandro Acero ,  Dong Yu

IPC分类号： G10L19/00

CPC分类号： G06F17/30707 ,  G06F17/2785 ,  G10L15/26

摘要： A method of aiding a speech recognition program developer by grouping calls passing through an identified question-answer (QA) state or transition into clusters based on causes of problems associated with the calls is provided. The method includes determining a number of clusters into which a plurality of calls will be grouped. Then, the plurality of calls is at least partially randomly assigned to the different clusters. Model parameters are estimated using clustering information based upon the assignment of the plurality of calls to the different clusters. Individual probabilities are calculated for each of the plurality of calls using the estimated model parameters. The individual probabilities are indicative of a likelihood that the corresponding call belongs to a particular cluster. The plurality of calls is then re-assigned to the different clusters based upon the calculated probabilities. These steps are then repeated until the grouping of the plurality of calls achieves a desired stability.

摘要翻译： 提供了一种通过将通过识别的问答（QA）状态的呼叫或基于与呼叫相关联的问题的原因转换成群集的呼叫来帮助语音识别程序开发者的方法。 该方法包括确定将多个呼叫分组到的群集的数量。 然后，多个呼叫至少部分地被随机分配给不同的群集。 基于对不同簇的多个呼叫的分配，使用聚类信息估计模型参数。 使用估计的模型参数为多个呼叫中的每一个计算单个概率。 单个概率表示相应呼叫属于特定集群的可能性。 然后，基于所计算的概率，将多个呼叫重新分配给不同的群集。 然后重复这些步骤直到多个呼叫的分组达到期望的稳定性。

公开(公告)号：US20110137639A1

公开(公告)日：2011-06-09

申请号：US13027921

申请日：2011-02-15

申请人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

发明人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

IPC分类号： G06F17/27

CPC分类号： G10L15/063 ,  G10L15/197

摘要： A statistical language model is trained for use in a directory assistance system using the data in a directory assistance listing corpus. Calculations are made to determine how important words in the corpus are in distinguishing a listing from other listings, and how likely words are to be omitted or added by a user. The language model is trained using these calculations.

摘要翻译： 训练统计语言模型，以使用目录援助列表语料库中的数据在目录辅助系统中使用。 进行计算，以确定语料库中的单词在区分列表和其他列表中的重要程度以及用户可能忽略或添加单词的可能性。 使用这些计算训练语言模型。

公开(公告)号：US07949526B2

公开(公告)日：2011-05-24

申请号：US11810086

申请日：2007-06-04

申请人： Yun-Cheng Ju ,  Alejandro Acero ,  Neal Bernstein ,  Geoffrey Zweig

发明人： Yun-Cheng Ju ,  Alejandro Acero ,  Neal Bernstein ,  Geoffrey Zweig

IPC分类号： G10L15/00

CPC分类号： G10L15/005 ,  G10L17/26 ,  H04M3/4211 ,  H04M3/4878 ,  H04M3/493 ,  H04M2201/40

摘要： A voice interaction system is configured to analyze an utterance and identify inherent attributes that are indicative of a demographic characteristic of the system user that spoke the utterance. The system then selects and presents a personalized response to the user, the response being selected based at least in part on the identified demographic characteristic. In one embodiment, the demographic characteristic is one or more of the caller's age, gender, ethnicity, education level, emotional state, health status and geographic group. In another embodiment, the selection of the response is further based on consideration of corroborative caller data.

摘要翻译： 语音交互系统被配置为分析话语并且识别指示说话的系统用户的人口特征的固有属性。 然后，系统选择并向用户呈现个性化的响应，至少部分地基于所识别的人口特征来选择响应。 在一个实施例中，人口特征是呼叫者的年龄，性别，种族，教育水平，情绪状态，健康状况和地理组中的一个或多个。 在另一个实施例中，响应的选择进一步基于对确认呼叫者数据的考虑。

公开(公告)号：US07860707B2

公开(公告)日：2010-12-28

申请号：US11638071

申请日：2006-12-13

申请人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

发明人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju

IPC分类号： G06F17/28

CPC分类号： G06F17/2755

摘要： A computer-implemented method is disclosed for improving the accuracy of a directory assistance system. The method includes constructing a prefix tree based on a collection of alphabetically organized words. The prefix tree is utilized as a basis for generating splitting rules for a compound word included in an index associated with the directory assistance system. A language model check and a pronunciation check are conducted in order to determine which of the generated splitting rules are mostly likely correct. The compound word is split into word components based on the most likely correct rule or rules. The word components are incorporated into a data set associated with the directory assistance system, such as into a recognition grammar and/or the index.

摘要翻译： 公开了一种用于提高目录辅助系统的准确性的计算机实现的方法。 该方法包括基于字母组织的字的集合构建前缀树。 前缀树被用作为包括在与目录辅助系统相关联的索引中的复合词生成分割规则的基础。 进行语言模型检查和发音检查，以确定哪些生成的分裂规则最可能是正确的。 复合词根据最可能的正确规则或规则分为单词组成部分。 单词组件被合并到与目录辅助系统相关联的数据集中，诸如识别语法和/或索引。

公开(公告)号：US07860314B2

公开(公告)日：2010-12-28

申请号：US10977871

申请日：2004-10-29

申请人： Ciprian I. Chelba ,  Alejandro Acero

发明人： Ciprian I. Chelba ,  Alejandro Acero

IPC分类号： G06K9/00

CPC分类号： G06F17/273 ,  G06K9/6297

摘要： A method and apparatus are provided for adapting an exponential probability model. In a first stage, a general-purpose background model is built from background data by determining a set of model parameters for the probability model based on a set of background data. The background model parameters are then used to define a prior model for the parameters of an adapted probability model that is adapted and more specific to an adaptation data set of interest. The adaptation data set is generally of much smaller size than the background data set. A second set of model parameters are then determined for the adapted probability model based on the set of adaptation data and the prior model.

摘要翻译： 提供了一种适应指数概率模型的方法和装置。 在第一阶段，通过基于一组背景数据确定概率模型的一组模型参数，从背景数据构建通用背景模型。 背景模型参数然后用于定义适应性概率模型的参数的先验模型，其适应并且更具体于感兴趣的自适应数据集。 自适应数据集通常比背景数据集小得多的大小。 然后，基于适配数据集和先​​验模型，针对适应概率模型确定第二组模型参数。

公开(公告)号：US07734460B2

公开(公告)日：2010-06-08

申请号：US11311951

申请日：2005-12-20

申请人： Dong Yu ,  Li Deng ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Alejandro Acero

IPC分类号： G06F17/21 ,  G06F17/27 ,  G10L15/00

CPC分类号： G10L15/08 ,  G10L15/187

摘要： A time-asynchronous lattice-constrained search algorithm is developed and used to process a linguistic model of speech that has a long-contextual-span capability. In the algorithm, nodes and links in the lattices developed from the model are expanded via look-ahead. Heuristics as utilized by a search algorithm are estimated. Additionally, pruning strategies can be applied to speed up the search.

摘要翻译： 开发了时间异步网格约束搜索算法，用于处理具有长语境跨度能力的语言语言模型。 在算法中，从模型开发的网格中的节点和链接通过预先扩展。 估计搜索算法使用的启发式算法。 此外，可以应用修剪策略来加快搜索速度。