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. 发明授权

US06907570B2 Video and multimedia browsing while switching between views 有权
标题翻译：视频和多媒体浏览，同时切换视图
公开(公告)号：US06907570B2
公开(公告)日：2005-06-14
申请号：US09822035
申请日：2001-03-29
申请人： Arnon Amir , Dulce Beatriz Ponceleon , Savitha Srinivasan
发明人： Arnon Amir , Dulce Beatriz Ponceleon , Savitha Srinivasan
IPC分类号： G06F17/30 , G09G5/00
CPC分类号： G06F17/30017 , H04N21/478 , H04N21/4828 , H04N21/6587 , H04N21/8549
摘要： Preferred implementations of the invention permit a user to seamlessly switch from a first media stream to a second media stream in a synchronized way, such that the second media stream picks up where the first media stream left off. In this way, the user experiences events chronologically but without interruption. In a preferred implementation, a user watching a skim video switches to a full length video when, for example, the skim video reaches a frame that is of particular interest to the user. The full length video begins at a point corresponding to the frame in the skim video that is of interest to the user, without skipping over video segments, so that the user does not experience any time gaps in the story line.
摘要翻译：本发明的优选实现允许用户以同步的方式从第一媒体流无缝地切换到第二媒体流，使得第二媒体流拾取第一媒体流离开的位置。以这种方式，用户按时间顺序经历事件但不中断。在优选实施方式中，当例如滑动视频达到用户特别感兴趣的帧时，观看滑视频视频的用户切换到全长视频。全长视频从与用户感兴趣的滑动视频中的帧对应的点开始，而不跳过视频段，使得用户在故事行中不会遇到任何时间间隙。

2. 发明授权

US06185527B2 System and method for automatic audio content analysis for word spotting, indexing, classification and retrieval 有权
标题翻译：自动音频内容分析系统和方法，用于单词识别，索引，分类和检索
公开(公告)号：US06185527B2
公开(公告)日：2001-02-06
申请号：US09234663
申请日：1999-01-19
申请人： Dragutin Petkovic , Dulce Beatriz Ponceleon , Savitha Srinivasan
发明人： Dragutin Petkovic , Dulce Beatriz Ponceleon , Savitha Srinivasan
IPC分类号： G10L1508
CPC分类号： G06F17/30775 , G06F17/30746 , G10H2210/046 , G10H2210/061 , G10L15/26 , G10L2015/088
摘要： A system and method for indexing an audio stream for subsequent information retrieval and for skimming, gisting, and summarizing the audio stream includes using special audio prefiltering such that only relevant speech segments that are generated by a speech recognition engine are indexed. Specific indexing features are disclosed that improve the precision and recall of an information retrieval system used after indexing for word spotting. The invention includes rendering the audio stream into intervals, with each interval including one or more segments. For each segment of an interval it is determined whether the segment exhibits one or more predetermined audio features such as a particular range of zero crossing rates, a particular range of energy, and a particular range of spectral energy concentration. The audio features are heuristically determined to represent respective audio events including silence, music, speech, and speech on music. Also, it is determined whether a group of intervals matches a heuristically predefined meta pattern such as continuous uninterrupted speech, concluding ideas, hesitations and emphasis in speech, and so on, and the audio stream is then indexed based on the interval classification and meta pattern matching, with only relevant features being indexed to improve subsequent precision of information retrieval. Also, alternatives for longer terms generated by the speech recognition engine are indexed along with respective weights, to improve subsequent recall.
摘要翻译：用于索引音频流以用于后续信息检索和用于撇号，提示和汇总音频流的系统和方法包括使用特殊音频预过滤器，使得只有由语音识别引擎生成的相关语音片段被索引。公开了特定的索引特征，其提高了用于单词识别的索引之后使用的信息检索系统的精度和调用。本发明包括将音频流呈现为间隔，每个间隔包括一个或多个段。对于间隔的每个段，确定该段是否呈现一个或多个预定的音频特征，例如零交叉率的特定范围，特定的能量范围和频谱能量集中的特定范围。音频特征被启发式地确定为表示各种音频事件，包括静音，音乐，语音和音乐上的语音。此外，确定一组间隔是否与启发式预定义的元模式匹配，例如连续不间断语音，结语，犹豫和语音强调等，然后基于间隔分类和元模式对音频流进行索引匹配，只有相关功能被索引，以提高信息检索的后续精度。此外，由语音识别引擎产生的较长项目的替代方案与相应的权重一起索引，以改进后续的召回。

3. 发明授权

US06636238B1 System and method for linking an audio stream with accompanying text material 有权
标题翻译：将音频流与伴随的文本材料相链接的系统和方法
公开(公告)号：US06636238B1
公开(公告)日：2003-10-21
申请号：US09295076
申请日：1999-04-20
申请人： Arnon Amir , Carlton Wayne Niblack , Norman Jerome Pass , Dragutin Petkovic , Dulce Beatriz Ponceleon , Savitha Srinivasan , Tanveer Fathima Syeda-Mahood
发明人： Arnon Amir , Carlton Wayne Niblack , Norman Jerome Pass , Dragutin Petkovic , Dulce Beatriz Ponceleon , Savitha Srinivasan , Tanveer Fathima Syeda-Mahood
IPC分类号： G06F1721
CPC分类号： G06F17/3074 , G06F17/30023 , G06F17/30064 , G06F17/30746
摘要： A system enables a user to query for key words and phrases a text document, such as a presentation slide file, and an associated audio stream, such as can be derived from an audio-video recording that is made of a presenter contemporaneously with the showing of the slides to an audience. A graphical user interface is presented in which query results for both the text document and the audio stream are displayed in a time-aligned format, to enable a user to easily and conveniently browse the text document and accompanying time-aligned audio stream based on the key words/phrases.
摘要翻译：系统使得用户能够查询关键词和短语，诸如呈现幻灯片文件和相关联的音频流之类的文本文档，例如可以从由演示者同时显示的音频 - 视频记录导出的幻灯片到观众。呈现图形用户界面，其中以时间对齐的格式显示文本文档和音频流的查询结果，以使得用户能够容易地和方便地浏览文本文档和伴随的时间对齐的音频流，基于关键词/短语

4. 发明授权

US06928407B2 System and method for the automatic discovery of salient segments in speech transcripts 有权
标题翻译：自动发现语音成绩单中显着部分的系统和方法
公开(公告)号：US06928407B2
公开(公告)日：2005-08-09
申请号：US10109960
申请日：2002-03-29
申请人： Dulce Beatriz Ponceleon , Savitha Srinivasan
发明人： Dulce Beatriz Ponceleon , Savitha Srinivasan
IPC分类号： G10L15/18 , G10L15/04 , G06F17/27
CPC分类号： G10L15/1822 , Y10S707/99937
摘要： A system and associated method automatically discover salient segments in a speech transcript and focus on the segmentation of an audio/video source into topically cohesive segments based on Automatic Speech Recognition (ASR) transcriptions. The word n-grams are extracted from the speech transcript using a three-phase segmentation algorithm based on the following sequence or combination of boundary-based and content-based methods: a boundary-based method; a rate of arrival of feature method; and a content-based method. In the first two segmentation passes, the temporal proximity and the rate of arrival of features are analyzed to compute an initial segmentation. In the third segmentation pass, changes in the set of content-bearing words used by adjacent segments are detected, to validate the initial segments for merging them, to prevent over-segmentation.
摘要翻译：系统和相关方法自动发现语音录音中的突出部分，并将焦点集中在基于自动语音识别（ASR）转录的音频/视频源到局部内聚片段中。使用基于边界和基于内容的方法的以下序列或组合的三阶段分割算法从语音转录中提取单词n-gram：基于边界的方法; 特征法的到达率; 和基于内容的方法。在前两个分割段中，分析特征的时间接近度和到达速率以计算初始分割。在第三个分割段中，检测相邻段使用的含有内容的单词集合中的变化，以验证其合并的初始段，以防止过度分割。

5. 发明授权

US08112413B2 System and service for automatically and dynamically composing document management applications 失效
标题翻译：用于自动和动态组合文档管理应用程序的系统和服务
公开(公告)号：US08112413B2
公开(公告)日：2012-02-07
申请号：US12210310
申请日：2008-09-15
申请人： Vikas Krishna , Savitha Srinivasan
发明人： Vikas Krishna , Savitha Srinivasan
IPC分类号： G06F7/00
CPC分类号： G06F17/30997 , G06K9/2054 , G06K2209/01 , G06Q10/04 , G06Q10/10
摘要： A document management system applies relevant document analysis, metadata extraction, and business process association algorithms and methodology to automatically and dynamically classify documents for routing, processing, and executing customized business logic. The document management system accepts documents from one or more channels, classifies the document and extracts metadata, executes customized application profiles and triggers business logic associated with the process. The document management system comprises a rules engine to detect and classify unstructured forms as well as structured forms, where the locations of attributes and visual layout are not fixed. The document management system provides automatic linkage between disparate systems that manages documents for the complete execution of a business process.
摘要翻译：文档管理系统应用相关文档分析，元数据提取和业务流程关联算法和方法来自动和动态地分类用于路由，处理和执行定制业务逻辑的文档。文档管理系统从一个或多个通道接收文档，对文档进行分类并提取元数据，执行定制的应用程序配置文件并触发与该过程相关联的业务逻辑。文档管理系统包括用于检测和分类非结构化表单以及结构化表单的规则引擎，其中属性和视觉布局的位置不是固定的。文档管理系统在管理用于完整执行业务流程的文档的不同系统之间提供自动链接。

6. 发明申请

US20070094057A1 System and method for automatic computation of validation metrics for global logistics processes 失效
标题翻译：用于自动计算全球物流流程验证度量的系统和方法
公开(公告)号：US20070094057A1
公开(公告)日：2007-04-26
申请号：US11181007
申请日：2005-07-12
申请人： Jennifer Kissner , Vikas Krishna , Scott Pollyea , Savitha Srinivasan
发明人： Jennifer Kissner , Vikas Krishna , Scott Pollyea , Savitha Srinivasan
IPC分类号： G06F9/44
CPC分类号： G06Q10/08 , G06Q10/0633 , G06Q10/06393 , G06Q30/0203
摘要： A validation matrix computation system automatically computes a validation matrix to analyze performance and efficiency of a global logistics process. The present system comprises identifying metrics and automatically computing the metrics to derive a validation matrix from the metrics. The system comprises a metric capture module installed at all participant locations in the global logistics process. The metric capture module captures, from logs generated at a node, metrics that measure performance at the node. The system generates the validation matrix from the captured metrics and uses the validation matrix to evaluate performance. The metrics comprise quantitative and qualitative metrics; quantitative metrics are automatically computed by correlating logs generated at the nodes and qualitative metrics are computed using surveys completed by participants in the global logistics process.
摘要翻译：验证矩阵计算系统自动计算验证矩阵，以分析全球后勤流程的绩效和效率。本系统包括识别度量并自动计算度量以从度量导出验证矩阵。该系统包括在全球物流过程中的所有参与者位置安装的度量捕获模块。度量捕获模块从节点生成的日志中捕获测量节点性能的指标。系统从捕获的指标生成验证矩阵，并使用验证矩阵来评估性能。指标包括定量和定性指标; 定量度量通过关联节点生成的日志自动计算，定性度量是使用全球后勤流程参与者完成的调查计算的。

7. 发明申请

US20080221917A1 METHOD AND SYSTEM FOR SPECIFYING, DEPLOYING AND DYNAMICALLY UPDATING WORK FLOWS 有权
标题翻译：用于指定，部署和动态更新工作流程的方法和系统
公开(公告)号：US20080221917A1
公开(公告)日：2008-09-11
申请号：US12124207
申请日：2008-05-21
申请人： Neil Harold Arthur Boyette , Issac Kam-Chak Cheng , Vikas Krishna , Savitha Srinivasan
发明人： Neil Harold Arthur Boyette , Issac Kam-Chak Cheng , Vikas Krishna , Savitha Srinivasan
IPC分类号： G06Q10/00
CPC分类号： G06Q10/10 , G06Q10/06
摘要： A method and system for specifying, deploying and updating work flows. A request is received from a user of a system with components comprising a computing system and human representatives. The components facilitate routing and servicing the request. A work flow comprising manual and automatic steps is specified to perform the routing and servicing of the request. The automatic steps are automatically performed by the computing system and the manual steps are manually performed by the representatives. Both the automatic steps and the manual steps are uniformly defined in a single general-purpose markup language (e.g., XML). Further, a manual step is dynamically transformed into a new automatic step that is represented as a new XML action element. The new XML action element includes an identifier of a software routine to be executed to perform the new automatic step.
摘要翻译：一种用于指定，部署和更新工作流程的方法和系统。从具有包括计算系统和人类代表的组件的系统的用户接收到请求。这些组件便于路由和服务请求。指定包括手动和自动步骤的工作流程来执行请求的路由和服务。自动步骤由计算系统自动执行，手动步骤由代表手动执行。自动步骤和手动步骤均以单一通用标记语言（例如，XML）统一定义。此外，手动步骤被动态转换为新的自动步骤，其被表示为新的XML动作元素。新的XML动作元素包括要执行以执行新的自动步骤的软件例程的标识符。

8. 发明申请

US20070260500A1 Method and system for specifying, deploying and dynamically updating work flows 失效
标题翻译：用于指定，部署和动态更新工作流的方法和系统
公开(公告)号：US20070260500A1
公开(公告)日：2007-11-08
申请号：US11415788
申请日：2006-05-02
申请人： Neil Boyette , Isaac Cheng , Vikas Krishna , Savitha Srinivasan
发明人： Neil Boyette , Isaac Cheng , Vikas Krishna , Savitha Srinivasan
IPC分类号： G06F9/46
CPC分类号： G06Q10/10 , G06Q10/06
摘要： A method and system for specifying, deploying and updating work flows. A request is received from a user of a system with components comprising a computing system and human representatives. The components facilitate routing and servicing the request. A work flow comprising manual and automatic steps is specified to perform the routing and servicing of the request. The automatic steps are automatically performed by the computing system and the manual steps are manually performed by the representatives. Both the automatic steps and the manual steps are uniformly defined in a single general-purpose markup language (e.g., XML). Further, a manual step is dynamically transformed into a new automatic step that is represented as a new XML action element. The new XML action element includes an identifier of a software routine to be executed to perform the new automatic step.
摘要翻译：一种用于指定，部署和更新工作流程的方法和系统。从具有包括计算系统和人类代表的组件的系统的用户接收到请求。这些组件便于路由和服务请求。指定包括手动和自动步骤的工作流程来执行请求的路由和服务。自动步骤由计算系统自动执行，手动步骤由代表手动执行。自动步骤和手动步骤均以单一通用标记语言（例如，XML）统一定义。此外，手动步骤被动态转换为新的自动步骤，其被表示为新的XML动作元素。新的XML动作元素包括要执行以执行新的自动步骤的软件例程的标识符。

9. 发明授权

US5963666A Confusion matrix mediated word prediction 失效
标题翻译：混乱矩阵介导词预测
公开(公告)号：US5963666A
公开(公告)日：1999-10-05
申请号：US516785
申请日：1995-08-18
申请人： Tetsunosuke Fujisaki , Savitha Srinivasan
发明人： Tetsunosuke Fujisaki , Savitha Srinivasan
IPC分类号： G06K9/68 , G06F17/22 , G06K9/62 , G06K9/72
CPC分类号： G06K9/723 , G06K2209/01
摘要： A system and method for performing an incremental search using a character string returned by a recognizer on a confusion matrix encoded dictionary to predict a word in a handwriting input field of an application program. In the system and method, handwritten characters are input into a data entry field of an application program. The handwritten characters are recognized and assigned a cluster code. The string of characters is characterized by the cluster codes of the individual characters. The cluster codes of the string are compared with strings of cluster codes representing words in a dictionary. All or some of the matching words are displayed to the user, from which a selection can be made.
摘要翻译：一种使用由识别器在混淆矩阵编码字典上返回的字符串执行增量搜索以预测应用程序的手写输入字段中的单词的系统和方法。在系统和方法中，手写字符被输入到应用程序的数据输入字段中。识别手写字符并分配集群代码。字符串的特征是单个字符的集群代码。将字符串的集群代码与表示字典中的字的集群代码的字符串进行比较。所有或一些匹配的词被显示给用户，从中可以进行选择。

10. 发明授权

US08768983B2 Dynamic configuration of multiple sources and source types in a business process 有权
标题翻译：在业务流程中动态配置多个源和源类型
公开(公告)号：US08768983B2
公开(公告)日：2014-07-01
申请号：US11538673
申请日：2006-10-04
申请人： Alan Lee Kohlscheen , Vikas Krishna , Scott William Pollyea , Savitha Srinivasan
发明人： Alan Lee Kohlscheen , Vikas Krishna , Scott William Pollyea , Savitha Srinivasan
IPC分类号： G06F12/00 , G06F17/30
CPC分类号： G06F17/30144 , G06F17/30011 , G06Q10/10
摘要： A computer implemented method, data processing system, computer usable program code, and apparatus are provided for dynamically configuring a document sharing system. A document sharing system receives a first request to add a new image file type to the document sharing system. A configuration file is identified for the new image file type to form an identified configuration file. The new image file type is added to the identified configuration file and the identified configuration file is saved as a new configuration file. The new configuration file is used to access files without restarting or recoding the document sharing system.
摘要翻译：提供了计算机实现的方法，数据处理系统，计算机可用程序代码和装置，用于动态配置文档共享系统。文档共享系统接收向文档共享系统添加新的图像文件类型的第一请求。为新的图像文件类型识别配置文件以形成识别的配置文件。将新的映像文件类型添加到标识的配置文件中，并将已识别的配置文件另存为新的配置文件。新配置文件用于访问文件，而不重新启动或重新编码文档共享系统。

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