公开(公告)号：US20110066433A1

公开(公告)日：2011-03-17

申请号：US12561005

申请日：2009-09-16

申请人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Alistair D. CONKIE

发明人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Alistair D. CONKIE

IPC分类号： G10L15/00

CPC分类号： G10L15/07 ,  G10L15/04 ,  G10L15/063 ,  G10L15/083 ,  G10L15/14 ,  G10L15/22 ,  G10L15/28 ,  G10L15/32

摘要： Disclosed herein are methods, systems, and computer-readable storage media for automatic speech recognition. The method includes selecting a speaker independent model, and selecting a quantity of speaker dependent models, the quantity of speaker dependent models being based on available computing resources, the selected models including the speaker independent model and the quantity of speaker dependent models. The method also includes recognizing an utterance using each of the selected models in parallel, and selecting a dominant speech model from the selected models based on recognition accuracy using the group of selected models. The system includes a processor and modules configured to control the processor to perform the method. The computer-readable storage medium includes instructions for causing a computing device to perform the steps of the method.

摘要翻译： 这里公开了用于自动语音识别的方法，系统和计算机可读存储介质。 该方法包括选择一个说话者独立模型，并选择一个说话者依赖模型的数量，说话人依赖模型的数量是基于可用的计算资源，所选择的模型包括与说话者无关的模型和说话者依赖模型的数量。 该方法还包括使用所选择的模型中的每一个并行地识别话语，并且基于使用所选择的模型的组的识别精度从所选择的模型中选择主要语言模型。 该系统包括处理器和被配置为控制处理器执行该方法的模块。 计算机可读存储介质包括用于使计算设备执行该方法的步骤的指令。

公开(公告)号：US20120232902A1

公开(公告)日：2012-09-13

申请号：US13042671

申请日：2011-03-08

申请人： Enrico BOCCHIERI ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

发明人： Enrico BOCCHIERI ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

IPC分类号： G10L15/06

CPC分类号： G10L15/063 ,  G10L15/14

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating an acoustic model for use in speech recognition. A system configured to practice the method first receives training data and identifies non-contextual lexical-level features in the training data. Then the system infers sentence-level features from the training data and generates a set of decision trees by node-splitting based on the non-contextual lexical-level features and the sentence-level features. The system decorrelates training vectors, based on the training data, for each decision tree in the set of decision trees to approximate full-covariance Gaussian models, and then can train an acoustic model for use in speech recognition based on the training data, the set of decision trees, and the training vectors.

摘要翻译： 本文公开了用于生成用于语音识别的声学模型的系统，方法和非暂时的计算机可读存储介质。 被配置为练习该方法的系统首先接收训练数据并识别训练数据中的非上下文词汇级特征。 然后，该系统从训练数据推导出句子级特征，并基于非上下文词汇级特征和句子级特征，通过节点分割生成一组决策树。 该系统基于训练数据对训练数据进行解相关，对于决策树组中的每个决策树，以近似全协方差高斯模型，然后可以基于训练数据训练用于语音识别的声学模型，该集合 的决策树，以及训练矢量。

公开(公告)号：US20150348540A1

公开(公告)日：2015-12-03

申请号：US14287866

申请日：2014-05-27

申请人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Mazin GILBERT GILBERT ,  Vincent GOFFIN ,  Taniya Mishra

发明人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Mazin GILBERT GILBERT ,  Vincent GOFFIN ,  Taniya Mishra

IPC分类号： G10L15/18 ,  G10L15/26

CPC分类号： G10L15/063 ,  G10L15/01 ,  G10L15/18 ,  G10L15/26 ,  G10L2015/0635

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

摘要翻译： 这里公开了用于将显着权重分配给ASR模型的单词的系统，方法和非暂时计算机可读存储介质。 分配给ASR模型中的单词的显着性值基于以前的成绩单的人类感知判断。 这些显着性值被用作权重以修改ASR模型，使得将口头文档转换成抄本的加权ASR模型的结果为用户提供更准确和有用的转录。

公开(公告)号：US08892443B2

公开(公告)日：2014-11-18

申请号：US12638667

申请日：2009-12-15

申请人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

发明人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

IPC分类号： G10L15/19 ,  G06F17/28

CPC分类号： G10L15/08 ,  G06F17/289 ,  G10L15/19 ,  G10L15/197 ,  G10L25/54 ,  G10L2015/081 ,  G10L2015/228

摘要： Disclosed herein are systems, methods, and computer-readable storage media for a speech recognition application for directory assistance that is based on a user's spoken search query. The spoken search query is received by a portable device and portable device then determines its present location. Upon determining the location of the portable device, that information is incorporated into a local language model that is used to process the search query. Finally, the portable device outputs the results of the search query based on the local language model.

摘要翻译： 本文公开了用于基于用户的口语搜索查询的目录帮助的语音识别应用的系统，方法和计算机可读存储介质。 口头搜索查询由便携式设备接收，便携式设备随后确定其当前位置。 在确定便携式设备的位置时，该信息被并入用于处理搜索查询的本地语言模型中。 最后，便携式设备基于本地语言模型输出搜索查询的结果。

公开(公告)号：US08738375B2

公开(公告)日：2014-05-27

申请号：US13103665

申请日：2011-05-09

申请人： Andrej Ljolje ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Vincent Goffin ,  Taniya Mishra

发明人： Andrej Ljolje ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Vincent Goffin ,  Taniya Mishra

IPC分类号： G10L15/26

CPC分类号： G10L15/197 ,  G10L15/063 ,  G10L15/22

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

摘要翻译： 这里公开了用于将显着权重分配给ASR模型的单词的系统，方法和非暂时计算机可读存储介质。 分配给ASR模型中的单词的显着性值基于以前的成绩单的人类感知判断。 这些显着性值被用作权重以修改ASR模型，使得将口头文档转换成抄本的加权ASR模型的结果为用户提供更准确和有用的转录。

公开(公告)号：US09679561B2

公开(公告)日：2017-06-13

申请号：US13072920

申请日：2011-03-28

申请人： Srinivas Bangalore ,  Robert Bell ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Patrick Haffner

发明人： Srinivas Bangalore ,  Robert Bell ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Patrick Haffner

IPC分类号： G10L15/183 ,  G10L15/30 ,  G10L15/22 ,  G10L15/06 ,  G10L15/065

CPC分类号： G10L15/183 ,  G10L15/06 ,  G10L15/065 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/0635 ,  G10L2015/0636 ,  G10L2015/228

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition models when a speech recognizer does not have access to a speech recognition model for that domain of interest and when available domain-specific data is below a minimum desired threshold to create a new domain-specific speech recognition model. A system configured to practice the method identifies a speech recognition domain and combines a set of speech recognition models, each speech recognition model of the set of speech recognition models being from a respective speech recognition domain. The system receives an amount of data specific to the speech recognition domain, wherein the amount of data is less than a minimum threshold to create a new domain-specific model, and tunes the combined speech recognition model for the speech recognition domain based on the data.

公开(公告)号：US09026444B2

公开(公告)日：2015-05-05

申请号：US12561005

申请日：2009-09-16

申请人： Andrej Ljolje ,  Diamantino Antonio Caseiro ,  Alistair D. Conkie

发明人： Andrej Ljolje ,  Diamantino Antonio Caseiro ,  Alistair D. Conkie

IPC分类号： G10L15/22 ,  G10L15/07 ,  G10L15/06

CPC分类号： G10L15/07 ,  G10L15/04 ,  G10L15/063 ,  G10L15/083 ,  G10L15/14 ,  G10L15/22 ,  G10L15/28 ,  G10L15/32

摘要： Disclosed herein are methods, systems, and computer-readable storage media for automatic speech recognition. The method includes selecting a speaker independent model, and selecting a quantity of speaker dependent models, the quantity of speaker dependent models being based on available computing resources, the selected models including the speaker independent model and the quantity of speaker dependent models. The method also includes recognizing an utterance using each of the selected models in parallel, and selecting a dominant speech model from the selected models based on recognition accuracy using the group of selected models. The system includes a processor and modules configured to control the processor to perform the method. The computer-readable storage medium includes instructions for causing a computing device to perform the steps of the method.

摘要翻译： 这里公开了用于自动语音识别的方法，系统和计算机可读存储介质。 该方法包括选择一个说话者独立模型，并选择一个说话者依赖模型的数量，说话人依赖模型的数量是基于可用的计算资源，所选择的模型包括与说话者无关的模型和说话者依赖模型的数量。 该方法还包括使用所选择的模型中的每一个并行地识别话语，并且基于使用所选择的模型的组的识别精度从所选择的模型中选择主要语言模型。 该系统包括处理器和被配置为控制处理器执行该方法的模块。 计算机可读存储介质包括用于使计算设备执行该方法的步骤的指令。

公开(公告)号：US08990085B2

公开(公告)日：2015-03-24

申请号：US12570757

申请日：2009-09-30

申请人： Andrej Ljolje ,  Diamantino Antonio Caseiro

发明人： Andrej Ljolje ,  Diamantino Antonio Caseiro

IPC分类号： G10L21/00 ,  G10L15/00 ,  G10L15/065 ,  G10L15/183 ,  G10L15/22

CPC分类号： G10L15/1815 ,  G10L15/063 ,  G10L15/065 ,  G10L15/183 ,  G10L15/22

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for handling expected repeat speech queries or other inputs. The method causes a computing device to detect a misrecognized speech query from a user, determine a tendency of the user to repeat speech queries based on previous user interactions, and adapt a speech recognition model based on the determined tendency before an expected repeat speech query. The method can further include recognizing the expected repeat speech query from the user based on the adapted speech recognition model. Adapting the speech recognition model can include modifying an acoustic model, a language model, and a semantic model. Adapting the speech recognition model can also include preparing a personalized search speech recognition model for the expected repeat query based on usage history and entries in a recognition lattice. The method can include retaining unmodified speech recognition models with adapted speech recognition models.

摘要翻译： 本文公开了用于处理预期重复语音查询或其他输入的系统，计算机实现的方法和计算机可读存储介质。 该方法使得计算设备检测来自用户的误识别语音查询，确定用户基于先前用户交互重复语音查询的趋势，以及基于在预期重复语音查询之前确定的趋势来调整语音识别模型。 该方法还可以包括基于适应的语音识别模型识别来自用户的预期重复语音查询。 适应语音识别模型可以包括修改声学模型，语言模型和语义模型。 适应语音识别模型还可以包括基于使用历史和识别格中的条目为预期重复查询准备个性化搜索语音识别模型。 该方法可以包括使用适应的语音识别模型保留未修改的语音识别模型。

公开(公告)号：US20110077942A1

公开(公告)日：2011-03-31

申请号：US12570757

申请日：2009-09-30

申请人： Andrej LJOLJE ,  Diamantino Antonio Caseiro

发明人： Andrej LJOLJE ,  Diamantino Antonio Caseiro

IPC分类号： G10L15/06

CPC分类号： G10L15/1815 ,  G10L15/063 ,  G10L15/065 ,  G10L15/183 ,  G10L15/22

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for handling expected repeat speech queries or other inputs. The method causes a computing device to detect a misrecognized speech query from a user, determine a tendency of the user to repeat speech queries based on previous user interactions, and adapt a speech recognition model based on the determined tendency before an expected repeat speech query. The method can further include recognizing the expected repeat speech query from the user based on the adapted speech recognition model. Adapting the speech recognition model can include modifying an acoustic model, a language model, and/or a semantic model. Adapting the speech recognition model can also include preparing a personalized search speech recognition model for the expected repeat query based on usage history and entries in a recognition lattice. The method can include retaining unmodified speech recognition models with adapted speech recognition models.

摘要翻译： 本文公开了用于处理预期重复语音查询或其他输入的系统，计算机实现的方法和计算机可读存储介质。 该方法使得计算设备检测来自用户的误识别语音查询，确定用户基于先前用户交互重复语音查询的趋势，以及基于在预期重复语音查询之前确定的趋势来调整语音识别模型。 该方法还可以包括基于适应的语音识别模型识别来自用户的预期重复语音查询。 适应语音识别模型可以包括修改声学模型，语言模型和/或语义模型。 适应语音识别模型还可以包括基于使用历史和识别格中的条目为预期重复查询准备个性化搜索语音识别模型。 该方法可以包括使用适应的语音识别模型保留未修改的语音识别模型。

公开(公告)号：US09558738B2

公开(公告)日：2017-01-31

申请号：US13042671

申请日：2011-03-08

申请人： Enrico Bocchieri ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

发明人： Enrico Bocchieri ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/14

CPC分类号： G10L15/063 ,  G10L15/14

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating an acoustic model for use in speech recognition. A system configured to practice the method first receives training data and identifies non-contextual lexical-level features in the training data. Then the system infers sentence-level features from the training data and generates a set of decision trees by node-splitting based on the non-contextual lexical-level features and the sentence-level features. The system decorrelates training vectors, based on the training data, for each decision tree in the set of decision trees to approximate full-covariance Gaussian models, and then can train an acoustic model for use in speech recognition based on the training data, the set of decision trees, and the training vectors.

摘要翻译： 本文公开了用于生成用于语音识别的声学模型的系统，方法和非暂时的计算机可读存储介质。 被配置为练习该方法的系统首先接收训练数据并识别训练数据中的非上下文词汇级特征。 然后，该系统从训练数据推导出句子级特征，并基于非上下文词汇级特征和句子级特征，通过节点分割生成一组决策树。 该系统基于训练数据对训练数据进行解相关，对于决策树组中的每个决策树，以近似全协方差高斯模型，然后可以基于训练数据训练用于语音识别的声学模型，该集合 的决策树，以及训练矢量。