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

US20140214402A1 IMPLEMENTATION OF UNSUPERVISED TOPIC SEGMENTATION IN A DATA COMMUNICATIONS ENVIRONMENT 审中-公开
标题翻译：数据通信环境中不可分割的主题分段的实现
公开(公告)号：US20140214402A1
公开(公告)日：2014-07-31
申请号：US13750049
申请日：2013-01-25
申请人： Qian Diao , Venkata Ramana Rao Gadde
发明人： Qian Diao , Venkata Ramana Rao Gadde
IPC分类号： G06F17/21
CPC分类号： G06F17/2745
摘要： A method is provided in one example embodiment and includes extracting sentences from data, which comprises a speech transcript; tokenizing the plurality of sentences to develop for each of the plurality of sentences a sentence vector and at least one feature vector; and performing topic segmentation on the speech transcript using the sentence vectors and feature vectors, the topic segmentation resulting in a listing of segments corresponding to the speech transcript. In certain embodiments, the feature vector may be at least one of a cue word feature vector, a speaker change feature vector, and a scene change feature vector.
摘要翻译：在一个示例实施例中提供了一种方法，并且包括从数据中提取句子，其包括语音转录本; 对所述多个句子中的每一个开发令牌化所述多个句子的句子向量和至少一个特征向量; 以及使用所述句子向量和特征向量在所述语音转录本上执行主题分段，所述主题分段导致对应于所述语音转录的段的列表。在某些实施例中，特征向量可以是提示词特征向量，说话者改变特征向量和场景改变特征向量中的至少一个。

2. 发明授权

US07769593B2 Method and apparatus for active noise cancellation 有权
标题翻译：主动噪声消除的方法和装置
公开(公告)号：US07769593B2
公开(公告)日：2010-08-03
申请号：US11541282
申请日：2006-09-28
申请人： Anand Venkataraman , Venkata Ramana Rao Gadde , Martin Graciarena
发明人： Anand Venkataraman , Venkata Ramana Rao Gadde , Martin Graciarena
IPC分类号： G10L15/00
CPC分类号： G10L15/20 , G10L21/02 , G10L2015/088
摘要： In one embodiment, the present invention is a method and apparatus for active noise cancellation. In one embodiment, a method for recognizing user speech in an audio signal received by a media system (where the audio signal includes user speech and ambient audio output produced by the media system and/or other devices) includes canceling portions of the audio signal associated with the ambient audio output and applying speech recognition processing to an uncancelled remainder of the audio signal.
摘要翻译：在一个实施例中，本发明是用于主动噪声消除的方法和装置。在一个实施例中，用于识别由媒体系统（其中音频信号包括由媒体系统和/或其他设备产生的用户语音和环境音频输出）接收的音频信号中的用户语音的方法包括消除相关联的音频信号的部分与环境音频输出并且将语音识别处理应用于音频信号的未被取消的剩余部分。

3. 发明授权

US07571095B2 Method and apparatus for recognizing speech in a noisy environment 有权
标题翻译：在嘈杂环境中识别语音的方法和装置
公开(公告)号：US07571095B2
公开(公告)日：2009-08-04
申请号：US11216669
申请日：2005-08-31
申请人： Martin Graciarena , Horacio Franco , Venkata Ramana Rao Gadde
发明人： Martin Graciarena , Horacio Franco , Venkata Ramana Rao Gadde
IPC分类号： G10L15/20
CPC分类号： G10L15/20
摘要： An apparatus and a concomitant method for recognizing speech in a noisy environment are provided. The present method includes applying a first interpolation weight to a clean speech model to produce a weighted clean speech model, applying a second interpolation weight to a noise model to produce a weighted noise model, and deriving a noisy speech model directly from the weighted clean speech model and the weighted noise model. At least one of the first interpolation weight and the second interpolation weight is computed in a maximum likelihood framework.
摘要翻译：提供了一种用于在嘈杂环境中识别语音的装置和伴随方法。本方法包括对干净的语音模型应用第一内插权重以产生加权的干净语音模型，将第二内插权重应用于噪声模型以产生加权噪声模型，以及从加权干净语音直接导出噪声语音模型模型和加权噪声模型。在最大似然框架中计算第一插值权重和第二插值权重中的至少一个。

4. 发明授权

US06725195B2 Method and apparatus for probabilistic recognition using small number of state clusters 有权
标题翻译：使用少量状态簇的概率识别的方法和装置
公开(公告)号：US06725195B2
公开(公告)日：2004-04-20
申请号：US10029420
申请日：2001-10-22
申请人： Ananth Sankar , Venkata Ramana Rao Gadde
发明人： Ananth Sankar , Venkata Ramana Rao Gadde
IPC分类号： G10L1514
CPC分类号： G10L15/06 , G10L15/144 , G10L2015/0631
摘要： Probabilistic recognition using clusters and simple probability functions provides improved performance by employing a limited number of clusters each using a relatively large number of simple probability functions. The simple probability functions for each of the limited number of state clusters are greater in number than the limited number of state clusters.
摘要翻译：使用群集和简单概率函数的概率识别通过采用有限数量的群集来提供改进的性能，每个簇使用相对大量的简单概率函数。有限数量的状态簇中的每一个的简单概率函数在数量上大于有限数量的状态簇。

5. 发明授权

US07533020B2 Method and apparatus for performing relational speech recognition 有权
标题翻译：执行关系语音识别的方法和装置
公开(公告)号：US07533020B2
公开(公告)日：2009-05-12
申请号：US11063357
申请日：2005-02-23
申请人： James F. Arnold , Michael W. Frandsen , Anand Venkataraman , Douglas A. Bercow , Gregory K. Myers , David J. Israel , Venkata Ramana Rao Gadde , Horacio Franco , Harry Bratt
发明人： James F. Arnold , Michael W. Frandsen , Anand Venkataraman , Douglas A. Bercow , Gregory K. Myers , David J. Israel , Venkata Ramana Rao Gadde , Horacio Franco , Harry Bratt
IPC分类号： G10L15/18
CPC分类号： G10L15/183 , G10L15/065
摘要： A method and apparatus are provided for performing speech recognition using observable and meaningful relationships between words within a single utterance and using a structured data source as a source of constraints on the recognition process. Results from a first constrained speech recognition pass can be combined with information about the observable and meaningful word relationships to constrain or simplify subsequent recognition passes. This iterative process greatly reduces the search space required for each recognition pass, making the speech recognition process more efficient, faster and accurate.
摘要翻译：提供了一种方法和装置，用于使用单个话语中的单词之间的可观察和有意义的关系来执行语音识别，并且使用结构化数据源作为识别过程的约束来源。来自第一约束语音识别通行证的结果可以与关于可观察和有意义的词关系的信息组合以约束或简化后续的识别通行证。这种迭代过程大大减少了每个识别通过所需的搜索空间，使得语音识别过程更加高效，更快速和准确。

6. 发明申请

US20080082326A1 Method and apparatus for active noise cancellation 有权
标题翻译：主动噪声消除的方法和装置
公开(公告)号：US20080082326A1
公开(公告)日：2008-04-03
申请号：US11541282
申请日：2006-09-28
申请人： Anand Venkataraman , Venkata Ramana Rao Gadde , Martin Graciarena
发明人： Anand Venkataraman , Venkata Ramana Rao Gadde , Martin Graciarena
IPC分类号： G10L21/02
CPC分类号： G10L15/20 , G10L21/02 , G10L2015/088
摘要： In one embodiment, the present invention is a method and apparatus for active noise cancellation. In one embodiment, a method for recognizing user speech in an audio signal received by a media system (where the audio signal includes user speech and ambient audio output produced by the media system and/or other devices) includes canceling portions of the audio signal associated with the ambient audio output and applying speech recognition processing to an uncancelled remainder of the audio signal.
摘要翻译：在一个实施例中，本发明是用于主动噪声消除的方法和装置。在一个实施例中，用于识别由媒体系统（其中音频信号包括由媒体系统和/或其他设备产生的用户语音和环境音频输出）接收的音频信号中的用户语音的方法包括消除相关联的音频信号的部分与环境音频输出并且将语音识别处理应用于音频信号的未被取消的剩余部分。

7. 发明申请

US20160092787A1 BEHAVIORAL MODELING OF A DATA CENTER UTILIZING HUMAN KNOWLEDGE TO ENHANCE A MACHINE LEARNING ALGORITHM 审中-公开
标题翻译：数据中心的行为建模利用人类知识来加强机器学习算法
公开(公告)号：US20160092787A1
公开(公告)日：2016-03-31
申请号：US14499270
申请日：2014-09-29
申请人： Venkata Ramana Rao Gadde , Rao Cherukuri
发明人： Venkata Ramana Rao Gadde , Rao Cherukuri
IPC分类号： G06N99/00 , G06N5/02
CPC分类号： G06N99/005 , G06N5/02
摘要： A method generates a behavioral model of a data center when a machine learning algorithm is applied. A team of human modelers that partition the data center into a plurality of connected nodes is analyzed by a behavioral model. The behavioral model of the data center detects an anomaly in a system behavior center by recursively applying the behavioral model to each node and simple component. A compressed metric vector for the node is generated by reducing a dimension of an input metric vector. A root cause of a failure caused is determined by the anomaly and an action is automatically recommended to an operator to resolve a problem caused by the failure. The proactively actions are taken to keep the data center in a normal state based on the behavioral model using the machine learning algorithm.
摘要翻译：当应用机器学习算法时，方法生成数据中心的行为模型。通过行为模型分析将数据中心分割成多个连接节点的人类建模者团队。数据中心的行为模型通过将行为模型递归地应用到每个节点和简单组件来检测系统行为中心的异常。通过减少输入度量向量的维度来生成节点的压缩度量向量。导致故障的根本原因是由异常决定的，并且自动建议操作人员解决由故障引起的问题的操作。采取主动措施，根据使用机器学习算法的行为模型，使数据中心保持正常状态。

8. 发明授权

US07120580B2 Method and apparatus for recognizing speech in a noisy environment 有权
公开(公告)号：US07120580B2
公开(公告)日：2006-10-10
申请号：US09930389
申请日：2001-08-15
申请人： Venkata Ramana Rao Gadde , Horacio Franco , John Butzberger
发明人： Venkata Ramana Rao Gadde , Horacio Franco , John Butzberger
IPC分类号： G10L15/20
CPC分类号： G10L15/20
摘要： An apparatus and a concomitant method for speech recognition. In one embodiment, the present method is referred to as a “Dynamic Noise Compensation” (DNC) method where the method estimates the models for noisy speech using models for clean speech and a noise model. Specifically, the model for the noisy speech is estimated by interpolation between the clean speech model and the noise model. This approach reduces computational cycles and does not require large memory capacity.

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