专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120150536A1 MODEL RESTRUCTURING FOR CLIENT AND SERVER BASED AUTOMATIC SPEECH RECOGNITION 失效
标题翻译：基于客户端和服务器的自动语音识别的模型重构
公开(公告)号：US20120150536A1
公开(公告)日：2012-06-14
申请号：US12964433
申请日：2010-12-09
申请人： Pierre Dognin , Vaibhava Goel , John R. Hershey , Peder A. Olsen
发明人： Pierre Dognin , Vaibhava Goel , John R. Hershey , Peder A. Olsen
IPC分类号： G10L15/00
CPC分类号： G10L15/144 , G10L15/30 , G10L2015/0636 , G10L2015/085
摘要： Access is obtained to a large reference acoustic model for automatic speech recognition. The large reference acoustic model has L states modeled by L mixture models, and the large reference acoustic model has N components. A desired number of components Nc, less than N, to be used in a restructured acoustic model derived from the reference acoustic model, is identified. The desired number of components Nc is selected based on a computing environment in which the restructured acoustic model is to be deployed. The restructured acoustic model also has L states. For each given one of the L mixture models in the reference acoustic model, a merge sequence is built which records, for a given cost function, sequential mergers of pairs of the components associated with the given one of the mixture models. A portion of the Nc components is assigned to each of the L states in the restructured acoustic model. The restructured acoustic model is built by, for each given one of the L states in the restructured acoustic model, applying the merge sequence to a corresponding one of the L mixture models in the reference acoustic model until the portion of the Nc components assigned to the given one of the L states is achieved.
摘要翻译：获得用于自动语音识别的大参考声学模型。大参考声学模型具有由L个混合模型建模的L状态，并且大的参考声学模型具有N个分量。识别在从参考声学模型导出的重构声学模型中使用的期望数量的小于N的分量Nc。基于要重新组织的声学模型要部署的计算环境来选择所需数量的分量Nc。重组的声学模型也有L个状态。对于参考声学模型中的每个给定的一个L混合模型，构建合并序列，其针对给定的成本函数记录与给定的混合模型相关联的成分对的顺序合并。 Nc分量的一部分被分配给重构的声学模型中的每个L状态。重构的声学模型由重构的声学模型中的每个给定的一个L状态构建，将合并序列应用于参考声学模型中的L个混合模型中的对应的一个，直到分配给给出了一个L状态。

2. 发明授权

US08635067B2 Model restructuring for client and server based automatic speech recognition 失效
标题翻译：基于客户端和服务器的自动语音识别模型重组
公开(公告)号：US08635067B2
公开(公告)日：2014-01-21
申请号：US12964433
申请日：2010-12-09
申请人： Pierre Dognin , Vaibhava Goel , John R. Hershey , Peder A. Olsen
发明人： Pierre Dognin , Vaibhava Goel , John R. Hershey , Peder A. Olsen
IPC分类号： G10L15/14
CPC分类号： G10L15/144 , G10L15/30 , G10L2015/0636 , G10L2015/085
摘要： Access is obtained to a large reference acoustic model for automatic speech recognition. The large reference acoustic model has L states modeled by L mixture models, and the large reference acoustic model has N components. A desired number of components Nc, less than N, to be used in a restructured acoustic model derived from the reference acoustic model, is identified. The desired number of components Nc is selected based on a computing environment in which the restructured acoustic model is to be deployed. The restructured acoustic model also has L states. For each given one of the L mixture models in the reference acoustic model, a merge sequence is built which records, for a given cost function, sequential mergers of pairs of the components associated with the given one of the mixture models. A portion of the Nc components is assigned to each of the L states in the restructured acoustic model. The restructured acoustic model is built by, for each given one of the L states in the restructured acoustic model, applying the merge sequence to a corresponding one of the L mixture models in the reference acoustic model until the portion of the Nc components assigned to the given one of the L states is achieved.
摘要翻译：获得用于自动语音识别的大参考声学模型。大参考声学模型具有由L个混合模型建模的L状态，并且大的参考声学模型具有N个分量。识别在从参考声学模型导出的重构声学模型中使用的期望数量的小于N的分量Nc。基于要重新组织的声学模型要部署的计算环境来选择所需数量的分量Nc。重组的声学模型也有L个状态。对于参考声学模型中的每个给定的一个L混合模型，构建合并序列，其针对给定的成本函数记录与给定的混合模型相关联的成分对的顺序合并。 Nc分量的一部分被分配给重构的声学模型中的每个L状态。重构的声学模型由重构的声学模型中的每个给定的一个L状态构建，将合并序列应用于参考声学模型中的L个混合模型中的对应的一个，直到分配给给出了一个L状态。

3. 发明申请

US20130317804A1 Method of Text Classification Using Discriminative Topic Transformation 有权
标题翻译：使用歧视主题变换的文本分类方法
公开(公告)号：US20130317804A1
公开(公告)日：2013-11-28
申请号：US13479656
申请日：2012-05-24
申请人： John R. Hershey , Jonathan Le Roux
发明人： John R. Hershey , Jonathan Le Roux
IPC分类号： G06F17/27
CPC分类号： G06F17/30286
摘要： Text is classified by determining text features from the text, and transforming the text features to topic features. Scores are determined for each topic features using a discriminative topic model. The model includes a classifier that operates on the topic features, wherein the topic features are determined by the transformation from the text features, and the transformation is optimized to maximize the scores of a correct class relative to the scores of incorrect classes. Then, a class label with a highest score is selected for the text. In situations where the classes are organized in a hierarchical structure, the discriminative topic models apply to classes at each level conditioned on previous levels and scores are combined across levels to evaluate the highest scoring class labels.
摘要翻译：通过从文本中确定文本特征并将文本特征转换为主题特征来分类文本。使用歧视主题模型为每个主题功能确定得分。该模型包括对主题特征进行操作的分类器，其中主题特征由文本特征的变换确定，并且优化变换以最大化相对于不正确类的分数的正确类的分数。然后，为文本选择具有最高分数的类标签。在类别以层次结构组织的情况下，歧视主题模型适用于以前级别条件下的每个级别的课程，并且分数在各级之间进行组合，以评估最高评分类标签。

4. 发明申请

US20110276307A1 Method and System for Registering an Object with a Probe Using Entropy-Based Motion Selection and Rao-Blackwellized Particle Filtering 有权
标题翻译：使用基于熵的运动选择和Rao-Blackwellized粒子滤波方法和系统注册探测器
公开(公告)号：US20110276307A1
公开(公告)日：2011-11-10
申请号：US13184311
申请日：2011-07-15
申请人： Yuichi Taguchi , Tim K. Marks , John R. Hershey
发明人： Yuichi Taguchi , Tim K. Marks , John R. Hershey
IPC分类号： G06F15/00
CPC分类号： B25J9/1694
摘要： A probe is registered with an object by probing the object with the probe at multiple poses, wherein each pose of the probe includes a location and an orientation. A probability distribution of a current location of the probe is represented by a set of particles, and a probability distribution of a current orientation of the probe is represented by a Gaussian distribution for each particle conditioned on the current location. A set of candidate motions is chosen, and for each candidate motion, an expected uncertainty based on the set of particles is determined. The candidate motion with a least expected uncertainty is selected as a next motion of the probe, the probe is moved according to the next motion, and the set of particles is updated using the next pose of the probe.
摘要翻译：通过用多个姿态探测物体探测对象，将物体注册到探针中，其中探针的每个姿态包括位置和方向。探针的当前位置的概率分布由一组粒子表示，并且探针的当前方向的概率分布由针对当前位置调节的每个粒子的高斯分布表示。选择一组候选运动，并且对于每个候选运动，确定基于该组粒子的预期不确定性。选择具有最少预期不确定性的候选运动作为探针的下一个运动，根据下一个运动移动探针，并使用探针的下一个姿势更新粒子集。

5. 发明授权

US07518631B2 Audio-visual control system 有权
标题翻译：视听系统
公开(公告)号：US07518631B2
公开(公告)日：2009-04-14
申请号：US11168124
申请日：2005-06-28
申请人： John R. Hershey , Zhengyou Zhang
发明人： John R. Hershey , Zhengyou Zhang
IPC分类号： H04N7/14
CPC分类号： G10L15/26
摘要： A visual control system controls a controlled component. In one embodiment, the visual control system controls the controlled component based on a visual location of a user. In another embodiment, input from a visual perception device is used to provide focus control for an audio input device. In additional embodiments, the visual control system stops, starts or suppresses speech recognition or other audio functions when the direction of the sound detected by the audio input device is not coming from the user's visual location.
摘要翻译：视觉控制系统控制受控组件。在一个实施例中，视觉控制系统基于用户的视觉位置来控制受控组件。在另一个实施例中，来自视觉感知设备的输入被用于为音频输入设备提供焦点控制。在另外的实施例中，当由音频输入设备检测到的声音的方向不是来自用户的视觉位置时，视觉控制系统停止，启动或抑制语音识别或其他音频功能。

6. 发明授权

US09251250B2 Method and apparatus for processing text with variations in vocabulary usage 有权
标题翻译：用于处理具有词汇使用变化的文本的方法和装置
公开(公告)号：US09251250B2
公开(公告)日：2016-02-02
申请号：US13433111
申请日：2012-03-28
申请人： John R. Hershey , Jonathan Le Roux , Creighton K Heakulani
发明人： John R. Hershey , Jonathan Le Roux , Creighton K Heakulani
IPC分类号： G06F17/27 , G06F17/21 , G10L15/00 , G10L15/18 , G06F17/30
CPC分类号： G06F17/30663 , G06F17/2785
摘要： Text is processed to construct a model of the text. The text has a shared vocabulary. The text is partitioned into sets and subsets of texts. The usage of the shared vocabulary in two or more sets is different, and the topics of two or more subsets are different. A probabilistic model is defined for the text. The probabilistic model considers each word in the text to be a token having a position and a word value, and the usage of the shared vocabulary, topics, subtopics, and word values for each token in the text are represented using distributions of random variables in the probabilistic model, wherein the random variables are discrete. Parameters are estimated for the model corresponding to the vocabulary usages, the word values, the topics, and the subtopics associated with the words.
摘要翻译：处理文本以构建文本的模型。该文本具有共享词汇。文本被分割成文本的集合和子集。在两个或多个集合中使用共享词汇是不同的，并且两个或更多个子集的主题是不同的。为文本定义概率模型。概率模型将文本中的每个单词视为具有位置和单词值的令牌，并且使用文本中每个标记的共享词汇表，主题，子主题和单词值的使用，使用随机变量的分布来表示概率模型，其中随机变量是离散的。对于与词汇相关联的词汇习惯，词汇值，主题和子主题的模型，估计参数。

7. 发明授权

US07486815B2 Method and apparatus for scene learning and three-dimensional tracking using stereo video cameras 有权
标题翻译：使用立体摄像机进行场景学习和三维跟踪的方法和装置
公开(公告)号：US07486815B2
公开(公告)日：2009-02-03
申请号：US10783709
申请日：2004-02-20
申请人： Trausti Kristjansson , Hagai Attias , John R. Hershey
发明人： Trausti Kristjansson , Hagai Attias , John R. Hershey
IPC分类号： G06K9/00 , H04N13/02 , H04N5/225
CPC分类号： G06K9/32 , G06T7/285
摘要： A method and apparatus are provided for learning a model for the appearance of an object while tracking the position of the object in three dimensions. Under embodiments of the present invention, this is achieved by combining a particle filtering technique for tracking the object's position with an expectation-maximization technique for learning the appearance of the object. Two stereo cameras are used to generate data for the learning and tracking.
摘要翻译：提供了一种方法和装置，用于在跟踪三维物体的位置的同时学习物体外观的模型。在本发明的实施例中，这是通过将用于跟踪对象的位置的粒子滤波技术与用于学习对象的外观的期望最大化技术组合来实现的。两个立体相机用于生成用于学习和跟踪的数据。

8. 发明授权

US09069798B2 Method of text classification using discriminative topic transformation 有权
标题翻译：使用歧视主题转换的文本分类方法
公开(公告)号：US09069798B2
公开(公告)日：2015-06-30
申请号：US13479656
申请日：2012-05-24
申请人： John R. Hershey , Jonathan Le Roux
发明人： John R. Hershey , Jonathan Le Roux
IPC分类号： G06F19/24 , G06F17/30
CPC分类号： G06F17/30286
摘要： Text is classified by determining text features from the text, and transforming the text features to topic features. Scores are determined for each topic features using a discriminative topic model. The model includes a classifier that operates on the topic features, wherein the topic features are determined by the transformation from the text features, and the transformation is optimized to maximize the scores of a correct class relative to the scores of incorrect classes. Then, a class label with a highest score is selected for the text. In situations where the classes are organized in a hierarchical structure, the discriminative topic models apply to classes at each level conditioned on previous levels and scores are combined across levels to evaluate the highest scoring class labels.
摘要翻译：通过从文本中确定文本特征并将文本特征转换为主题特征来分类文本。使用歧视主题模型为每个主题功能确定得分。该模型包括对主题特征进行操作的分类器，其中主题特征由文本特征的变换确定，并且优化变换以最大化相对于不正确类的分数的正确类的分数。然后，为文本选择具有最高分数的类标签。在类别以层次结构组织的情况下，歧视主题模型适用于以前级别条件下的每个级别的课程，并且分数在各级之间进行组合，以评估最高评分类标签。

9. 发明申请

US20130197904A1 Indirect Model-Based Speech Enhancement 有权
标题翻译：间接模型语言增强
公开(公告)号：US20130197904A1
公开(公告)日：2013-08-01
申请号：US13360467
申请日：2012-01-27
申请人： John R. Hershey , Jonathan Le Roux
发明人： John R. Hershey , Jonathan Le Roux
IPC分类号： G10L21/02
CPC分类号： G10L21/0216 , G10L21/0232
摘要： Enhanced speech is produced from a mixed signal including noise and the speech. The noise in the mixed signal is estimated using a vector-Taylor series. The estimated noise is in terms of a minimum mean-squared error. Then, the noise is subtracted from the mixed signal to obtain the enhanced speech.
摘要翻译：增强语音由混合信号产生，包括噪声和语音。使用向量 - 泰勒级数估计混合信号中的噪声。估计的噪声是以最小均方误差计。然后，从混合信号中减去噪声以获得增强的语音。

10. 发明授权

US07689413B2 Speech detection and enhancement using audio/video fusion 有权
标题翻译：使用音频/视频融合的语音检测和增强
公开(公告)号：US07689413B2
公开(公告)日：2010-03-30
申请号：US11852961
申请日：2007-09-10
申请人： John R. Hershey , Trausti Thor Kristajanson , Hagai Attias , Nebojsa Jojic
发明人： John R. Hershey , Trausti Thor Kristajanson , Hagai Attias , Nebojsa Jojic
IPC分类号： G10L21/02 , G10L11/00 , G06K9/00
CPC分类号： G10L15/065 , G10L15/20 , G10L15/25 , G10L25/78
摘要： A system and method facilitating speech detection and/or enhancement utilizing audio/video fusion is provided. The present invention fuses audio and video in a probabilistic generative model that implements cross-model, self-supervised learning, enabling rapid adaptation to audio visual data. The system can learn to detect and enhance speech in noise given only a short (e.g., 30 second) sequence of audio-visual data. In addition, it automatically learns to track the lips as they move around in the video.
摘要翻译：提供了利用音频/视频融合的促进语音检测和/或增强的系统和方法。本发明将音频和视频融合在实现跨模型，自我监督学习的概率生成模型中，使得能够快速适应视听数据。该系统可以学习仅在短（例如，30秒）的视听数据序列中检测和增强噪声中的语音。此外，它会自动学习在视频中移动时跟踪嘴唇。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式