专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US07848924B2 Method, apparatus and computer program product for providing voice conversion using temporal dynamic features 有权
标题翻译：用于使用时间动态特征提供语音转换的方法，装置和计算机程序产品
公开(公告)号：US07848924B2
公开(公告)日：2010-12-07
申请号：US11788263
申请日：2007-04-17
申请人： Jani K. Nurminen , Victor Popa , Jilei Tian
发明人： Jani K. Nurminen , Victor Popa , Jilei Tian
IPC分类号： G10L21/00
CPC分类号： G10L13/033
摘要： An apparatus for providing voice conversion using temporal dynamic features includes a feature extractor and a transformation element. The feature extractor may be configured to extract dynamic feature vectors from source speech. The transformation element may be in communication with the feature extractor and configured to apply a first conversion function to a signal including the extracted dynamic feature vectors to produce converted dynamic feature vectors. The first conversion function may have been trained using at least dynamic feature data associated with training source speech and training target speech. The transformation element may be further configured to produce converted speech based on an output of applying the first conversion function.
摘要翻译：用于使用时间动态特征提供语音转换的装置包括特征提取器和变换元件。特征提取器可以被配置为从源语音提取动态特征向量。变换元件可以与特征提取器通信并且被配置为将第一转换函数应用于包括所提取的动态特征向量的信号以产生转换的动态特征向量。可以使用至少与训练源语音和训练目标语音相关联的动态特征数据来训练第一转换功能。转换元件还可以被配置为基于应用第一转换函数的输出来产生转换的语音。

32. 发明申请

US20080004877A1 Method, Apparatus and Computer Program Product for Providing Adaptive Language Model Scaling 失效
标题翻译：提供自适应语言模型缩放的方法，设备和计算机程序产品
公开(公告)号：US20080004877A1
公开(公告)日：2008-01-03
申请号：US11427954
申请日：2006-06-30
申请人： Jilei Tian
发明人： Jilei Tian
IPC分类号： G10L15/04
CPC分类号： G10L15/197
摘要： An apparatus for providing adaptive language model scaling includes an adaptive scaling element and an interface element. The adaptive scaling element is configured to receive input speech comprising a sequence of spoken words and to determine a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words. Each corresponding sentence score is calculated using an adaptive scaling factor. The interface element is configured to receive a user input selecting one of the candidate sequences. The adaptive scaling element is further configured to estimate an objective function based on the user input and to modify the adaptive scaling factor based on the estimated objective function.
摘要翻译：用于提供自适应语言模型缩放的装置包括自适应缩放元素和接口元素。自适应缩放元件被配置为接收包括一系列口语单词的输入语音，并且确定多个候选序列的文本单词，其中候选序列中的每一个具有相应的句子分数，表示候选序列与口语使用自适应缩放因子计算每个相应的句子得分。接口元件被配置为接收选择候选序列之一的用户输入。自适应缩放元件还被配置为基于用户输入来估计目标函数，并且基于估计的目标函数修改自适应缩放因子。

33. 发明授权

US10853531B2 Method and apparatus for context sensing inference 有权
公开(公告)号：US10853531B2
公开(公告)日：2020-12-01
申请号：US14353601
申请日：2011-11-02
申请人： Xueying Li , Huanhuan Cao , Jilei Tian
发明人： Xueying Li , Huanhuan Cao , Jilei Tian
IPC分类号： G06F30/20 , H04L29/08 , H04W4/029 , G06F16/9535 , H04M1/725
摘要： The exemplary embodiments of the invention provide at least a method, apparatus and system to perform operations including receiving context data from an electronic device, causing, at least in part based on the received context data, an identification of at least one context model compatible with the electronic device, and causing, at least in part, provision of the electronic device with the at least one compatible context model. In addition, the exemplary embodiments of the invention further provide at least a method, apparatus and system to perform operations including causing, at least in part, a provision of context data associated with an electronic device to a context inference service, in response, receiving a context model from the context inference service, and causing adaptation of the received context model as a current context model of the electronic device.

34. 发明授权

US09665648B2 Method and apparatus for a user interest topology based on seeded user interest modeling 有权
公开(公告)号：US09665648B2
公开(公告)日：2017-05-30
申请号：US13637001
申请日：2010-03-29
申请人： Sailesh Sathish , Jilei Tian , Rile Hu
发明人： Sailesh Sathish , Jilei Tian , Rile Hu
IPC分类号： G06F17/30
CPC分类号： G06F17/30867 , G06F17/30734
摘要： Methods and apparatuses are provided for user interest modeling. A method may include receiving an input from a user for specifying one or more topics from among a predetermined hierarchy of topics and subtopics. The method may additionally include retrieving one or more documents associated with the user and extracting language tokens from the documents based, at least in part, on the specified topics. Corresponding apparatuses are also provided.

35. 发明授权

US09450984B2 Automatic approach for the personalized privacy recommendation related to the location 有权
标题翻译：自动方式为个人隐私建议相关的位置
公开(公告)号：US09450984B2
公开(公告)日：2016-09-20
申请号：US14350562
申请日：2011-10-17
申请人： Kuifei Yu , Huanhuan Cao , Jilei Tian
发明人： Kuifei Yu , Huanhuan Cao , Jilei Tian
IPC分类号： H04L29/06 , H04L29/08 , H04W8/16 , H04W12/02 , H04W4/02
CPC分类号： H04L63/20 , H04L67/18 , H04W4/02 , H04W8/16 , H04W12/02
摘要： A method for personalized location privacy recommendation comprises: obtaining information of one or more locations for a user; collecting features of the one or more locations; and recommending respective privacy levels of the one or more locations automatically based at least in part on the information and the features.
摘要翻译：一种用于个性化位置隐私推荐的方法包括：获取用户的一个或多个位置的信息; 收集一个或多个位置的特征; 并且至少部分地基于所述信息和特征来自动推荐所述一个或多个位置的各自的隐私级别。

36. 发明授权

US09414183B2 Method and apparatus for providing group context sensing and inference 有权
标题翻译：用于提供组语境感知和推理的方法和装置
公开(公告)号：US09414183B2
公开(公告)日：2016-08-09
申请号：US14375415
申请日：2012-03-20
申请人： Wei Wang , Huanhuan Cao , Jilei Tian , Xia Wang
发明人： Wei Wang , Huanhuan Cao , Jilei Tian , Xia Wang
IPC分类号： H04W4/00 , H04W8/24 , H04W4/02 , H04W4/08
CPC分类号： H04W4/38 , H04W4/02 , H04W4/08 , H04W8/24
摘要： An approach is provided for providing group context sensing and inference. The group context platform determines at least one group of one or more devices that have one or more group contexts that are at least substantially similar, at least substantially correlated, or a combination thereof. Next, the group context platform causes, at least in part, a distribution of one or more context sensing tasks among the one or more devices of the at least one group. Then, the group context platform processes and/or facilitates a processing of one or more results of the one or more context sensing tasks to (a) modify the one or more group contexts; (b) enhance the one or more group contexts; (c) determine one or more other group contexts; or (d) a combination thereof.
摘要翻译：提供了一种用于提供组语境感知和推理的方法。组上下文平台确定具有一个或多个组上下文至少基本相似，至少基本相关或其组合的一个或多个设备的至少一组。接下来，组上下文平台至少部分地导致至少一个组中的一个或多个设备中的一个或多个上下文感测任务的分布。然后，组上下文平台处理和/或促进对一个或多个上下文感测任务的一个或多个结果的处理，以（a）修改一个或多个组上下文; （b）加强一个或多个团体背景; （c）确定一个或多个其他组背景; 或（d）其组合。

37. 发明授权

US09301114B2 Method and apparatus for determining significant places 有权
标题翻译：确定重要场所的方法和装置
公开(公告)号：US09301114B2
公开(公告)日：2016-03-29
申请号：US14376526
申请日：2012-02-22
申请人： Huanhuan Cao , Jilei Tian
发明人： Huanhuan Cao , Jilei Tian
IPC分类号： H04W64/00 , H04W4/18 , G01S5/02 , G06Q30/02 , H04W4/02
CPC分类号： H04W4/185 , G01S5/02 , G06Q30/0259 , H04W4/021
摘要： An approach is provided for determining significant places with greatly improved accuracy using universally available identifier information. A significant place platform causes, at least in part, a mapping of one or more communication coverage areas associated with one or more identifiers onto at least one geo-grid, wherein the one or more identifiers are associated with at least one device operating within at least one communication network. The significant place platform further processes the one or more identifiers to determine one or more significance scores associated with one or more grid units of the at least one geo-grid. The significant place platform also determines at least one significant place based, at least in part, on the one or more significance scores.
摘要翻译：提供了一种用于使用普遍可用的标识符信息来确定大大提高精度的重要位置的方法。至少部分地，将一个或多个与一个或多个标识符相关联的通信覆盖区域映射到至少一个地理格栅上，其中所述一个或多个标识符与在其中操作的至少一个设备相关联，至少一个通信网络。重要的地方平台进一步处理一个或多个标识符以确定与至少一个地理格网的一个或多个网格单元相关联的一个或多个重要性得分。重要的地方平台还至少在一个或多个显着性得分上确定至少一个重要的地位。

38. 发明授权

US09294878B2 Method and apparatus for providing hub-based indexing and services 有权
标题翻译：用于提供基于集线器的索引和服务的方法和装置
公开(公告)号：US09294878B2
公开(公告)日：2016-03-22
申请号：US14379976
申请日：2012-02-29
申请人： Jilei Tian , Huanhuan Cao , Zhen Liu
发明人： Jilei Tian , Huanhuan Cao , Zhen Liu
IPC分类号： H04W4/02 , H04W4/18 , H04L29/08 , H04W88/02
CPC分类号： H04W4/023 , H04L67/20 , H04L67/306 , H04L67/325 , H04W4/029 , H04W4/18 , H04W88/02
摘要： An approach is provided for providing hub-based indexing and services. The hub-based platform causes, at least in part, an indexing of location-based content according to one or more location hubs of one or more transportation lines, Next, the hub-based platform determines a current proximity, a predicted proximity, or a combination thereof of one or more devices to the one or more location hubs, wherein the one or more devices are (a) traveling on the one or more transportation lines, (b) predicted to travel on the one or more transportation lines, or (c) a combination thereof. Then, the hub-based platform causes, at least in part, a presentation of at least a portion of the location-based content based, at least in part, on the current proximity, the predicted proximity, or a combination thereof.
摘要翻译：提供了一种提供基于中心的索引和服务的方法。基于集线器的平台至少部分地导致根据一个或多个传输线的一个或多个位置集线器对基于位置的内容进行索引。接下来，基于集线器的平台确定当前接近度，预测的接近度，或者一个或多个设备的组合到所述一个或多个位置轮毂，其中所述一个或多个设备是（a）在所述一条或多条运输线路上行驶，（b）预测在所述一条或多条运输线路上行驶，或（c）其组合。然后，基于集线器的平台至少部分地至少部分地基于当前接近度，预测接近度或其组合来呈现基于位置的内容的至少一部分。

39. 发明申请

US20150208203A1 METHOD AND APPARATUS FOR PROVIDING TRANSPORTATION BASED RECOMMENDER SYSTEM 审中-公开
标题翻译：提供基于运输的推荐系统的方法和装置
公开(公告)号：US20150208203A1
公开(公告)日：2015-07-23
申请号：US14409567
申请日：2012-06-25
申请人： Huanhuan Cao , Jilei Tian
发明人： Huanhuan Cao , Jilei Tian
IPC分类号： H04W4/02 , G06F17/30 , H04M1/725
CPC分类号： G06F16/29 , G06F16/9537 , H04M1/72569 , H04M1/72572 , H04W4/029
摘要： An approach for recommending location-based content items that account for locations with ease of access based on available transportation options is described. A content recommender platform determines one or more predicted locations of a user based, at least in part, on an ease of access from a location associated with the use. The content recommender platform determines one or more location-based content items associated with the one or more predicted locations, the location, or a combination thereof. The content recommender platform determines one or more recommended content items from among the one or more location-based content items. In this way, the recommended content items may be easily accessible and may accord with the user's preferences.
摘要翻译：描述了一种基于可用的交通选项来推荐基于位置的内容项目以便于访问的位置的方法。至少部分地，内容推荐器平台基于来自与使用相关联的位置的容易性来确定用户的一个或多个预测位置。内容推荐器平台确定与一个或多个预测位置，位置或其组合相关联的一个或多个基于位置的内容项。内容推荐器平台从一个或多个基于位置的内容项中确定一个或多个推荐内容项。以这种方式，推荐的内容项目可以容易地访问并且可以符合用户的偏好。

40. 发明授权

US08224648B2 Hybrid approach in voice conversion 失效
标题翻译：语音转换中的混合方法
公开(公告)号：US08224648B2
公开(公告)日：2012-07-17
申请号：US11966255
申请日：2007-12-28
申请人： Jilei Tian , Victor Popa , Jani Kristian Nurminen
发明人： Jilei Tian , Victor Popa , Jani Kristian Nurminen
IPC分类号： G01L13/06
CPC分类号： G10L21/00 , G10L2021/0135
摘要： A hybrid approach is described for combining frequency warping and Gaussian Mixture Modeling (GMM) to achieve better speaker identity and speech quality. To train the voice conversion GMM model, line spectral frequency and other features are extracted from a set of source sounds to generate a source feature vector and from a set of target sounds to generate a target feature vector. The GMM model is estimated based on the aligned source feature vector and the target feature vector. A mixture specific warping function is generated each set of mixture mean pairs of the GMM model, and a warping function is generated based on a weighting of each of the mixture specific warping functions. The warping function can be used to convert sounds received from a source speaker to approximate speech of a target speaker.
摘要翻译：描述了混合方法，用于组合频率扭曲和高斯混合建模（GMM），以实现更好的扬声器身份和语音质量。为了训练语音转换GMM模型，从一组源声音中提取线谱频率和其他特征以产生源特征向量和从一组目标声音生成目标特征向量。基于对齐的源特征向量和目标特征向量来估计GMM模型。每个GMM模型的混合均值对都产生混合特定的翘曲函数，并且基于每个混合特定翘曲函数的加权产生翘曲函数。翘曲功能可用于将从源扬声器接收的声音转换为目标扬声器的近似语音。

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