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

US07831425B2 Time-anchored posterior indexing of speech 有权
标题翻译：时间锚定的后向索引语音
公开(公告)号：US07831425B2
公开(公告)日：2010-11-09
申请号：US11300735
申请日：2005-12-15
申请人： Alejandro Acero , Asela J. Gunawardana , Ciprian I. Chelba , Erik W. Selberg , Frank Torsten B. Seide , Patrick Nguyen , Roger Peng Yu
发明人： Alejandro Acero , Asela J. Gunawardana , Ciprian I. Chelba , Erik W. Selberg , Frank Torsten B. Seide , Patrick Nguyen , Roger Peng Yu
IPC分类号： G10L15/04 , G10L15/00 , G10L15/28
CPC分类号： G10L15/08 , G10L15/05
摘要： A computer-implemented method of indexing a speech lattice for search of audio corresponding to the speech lattice is provided. The method includes identifying at least two speech recognition hypotheses for a word which have time ranges satisfying a criteria. The method further includes merging the at least two speech recognition hypotheses to generate a merged speech recognition hypothesis for the word.
摘要翻译：提供了一种用于索引用于搜索与语音格子相对应的音频的语音格子的计算机实现的方法。该方法包括识别具有满足标准的时间范围的单词的至少两个语音识别假设。该方法还包括合并至少两个语音识别假设以产生该单词的合并语音识别假设。

2. 发明授权

US07640272B2 Using automated content analysis for audio/video content consumption 有权
标题翻译：使用音频/视频内容消费的自动内容分析
公开(公告)号：US07640272B2
公开(公告)日：2009-12-29
申请号：US11635153
申请日：2006-12-07
申请人： Milind Mahajan , Patrick Nguyen , Alejandro Acero
发明人： Milind Mahajan , Patrick Nguyen , Alejandro Acero
IPC分类号： G06F7/00 , G06F17/00
CPC分类号： G10L15/18 , G06F17/30787 , G06F17/30796 , G06F17/30852 , Y10S707/99945 , Y10S707/99948
摘要： Audio/video (A/V) content is analyzed using speech and language analysis components. Metadata is automatically generated based upon the analysis. The metadata is used in generating user interface interaction components which allow a user to view subject matter in various segments of the A/V content and to interact with the A/V content based on the automatically generated metadata.
摘要翻译：使用语音和语言分析组件分析音频/视频（A / V）内容。基于分析自动生成元数据。元数据用于生成用户界面交互组件，其允许用户在A / V内容的各个段中查看主题，并且基于自动生成的元数据与A / V内容进行交互。

3. 发明授权

US09684741B2 Presenting search results according to query domains 有权
公开(公告)号：US09684741B2
公开(公告)日：2017-06-20
申请号：US12479371
申请日：2009-06-05
申请人： Xiao Li , Patrick Nguyen , Geoffrey Zweig , Alejandro Acero
发明人： Xiao Li , Patrick Nguyen , Geoffrey Zweig , Alejandro Acero
IPC分类号： G06F17/30 , G10L15/26 , G06N99/00
CPC分类号： G06F17/30991 , G06N99/005 , G10L15/26 , G10L2015/025
摘要： A query may be applied against search engines that respectively return a set of search results relating to various items discovered in the searched data sets. However, presenting numerous and varied search results may be difficult on mobile devices with small displays and limited computational resources. Instead, search results may be associated with search domains representing various information types (e.g., contacts, public figures, places, projects, movies, music, and books) and presented by grouping search results with associated query domains, e.g., in a tabbed user interface. The query may be received through an input device associated with a particular input domain, and may be transitioned to the query domain of a particular search engine (e.g., by recognizing phonemes of a voice query using an acoustic model; matching phonemes with query terms according to a pronunciation model; and generating a recognition result according to a vocabulary of an n-gram language model.)

4. 发明申请

US20080140385A1 Using automated content analysis for audio/video content consumption 有权
标题翻译：使用音频/视频内容消费的自动内容分析
公开(公告)号：US20080140385A1
公开(公告)日：2008-06-12
申请号：US11635153
申请日：2006-12-07
申请人： Milind Mahajan , Patrick Nguyen , Alejandro Acero
发明人： Milind Mahajan , Patrick Nguyen , Alejandro Acero
IPC分类号： G06F17/27 , G10L15/00
CPC分类号： G10L15/18 , G06F17/30787 , G06F17/30796 , G06F17/30852 , Y10S707/99945 , Y10S707/99948
摘要： Audio/video (A/V) content is analyzed using speech and language analysis components. Metadata is automatically generated based upon the analysis. The metadata is used in generating user interface interaction components which allow a user to view subject matter in various segments of the A/V content and to interact with the A/V content based on the automatically generated metadata.
摘要翻译：使用语音和语言分析组件分析音频/视频（A / V）内容。基于分析自动生成元数据。元数据用于生成用户界面交互组件，其允许用户在A / V内容的各个段中查看主题，并且基于自动生成的元数据与A / V内容进行交互。

5. 发明申请

US20100312782A1 PRESENTING SEARCH RESULTS ACCORDING TO QUERY DOMAINS 有权
标题翻译：根据查询域提供搜索结果
公开(公告)号：US20100312782A1
公开(公告)日：2010-12-09
申请号：US12479371
申请日：2009-06-05
申请人： Xiao Li , Patrick Nguyen , Geoffrey Zweig , Alejandro Acero
发明人： Xiao Li , Patrick Nguyen , Geoffrey Zweig , Alejandro Acero
IPC分类号： G06F17/30 , G10L15/26
CPC分类号： G06F17/30991 , G06N99/005 , G10L15/26 , G10L2015/025
摘要： A query may be applied against search engines that respectively return a set of search results relating to various items discovered in the searched data sets. However, presenting numerous and varied search results may be difficult on mobile devices with small displays and limited computational resources. Instead, search results may be associated with search domains representing various information types (e.g., contacts, public figures, places, projects, movies, music, and books) and presented by grouping search results with associated query domains, e.g., in a tabbed user interface. The query may be received through an input device associated with a particular input domain, and may be transitioned to the query domain of a particular search engine (e.g., by recognizing phonemes of a voice query using an acoustic model; matching phonemes with query terms according to a pronunciation model; and generating a recognition result according to a vocabulary of an n-gram language model.)
摘要翻译：可以针对分别返回与搜索到的数据集中发现的各种项目相关的一组搜索结果的搜索引擎应用查询。然而，在具有小显示器和有限的计算资源的移动设备上呈现多种多样的搜索结果可能是困难的。相反，搜索结果可以与表示各种信息类型（例如，联系人，公众人物，地点，项目，电影，音乐和书籍）的搜索域相关联，并且通过将搜索结果与相关联的查询域分组，例如在标签用户接口。可以通过与特定输入域相关联的输入设备来接收查询，并且可以将其转换到特定搜索引擎的查询域（例如，通过使用声学模型识别语音查询的音素;使用查询词语匹配音素发音模型;以及根据n-gram语言模型的词汇生成识别结果。）

6. 发明申请

US20080262995A1 Multimodal rating system 审中-公开
标题翻译：多模式评级系统
公开(公告)号：US20080262995A1
公开(公告)日：2008-10-23
申请号：US11788325
申请日：2007-04-19
申请人： Geoffrey Gerson Zweig , Yun-Cheng Ju , Patrick Nguyen , Alejandro Acero
发明人： Geoffrey Gerson Zweig , Yun-Cheng Ju , Patrick Nguyen , Alejandro Acero
IPC分类号： G06F17/30
CPC分类号： G06Q30/02
摘要： A method of communicating information about a product evaluation between a system having a data store and a wireless client device is discussed. The method includes receiving a signal representative of an audible indication from the client device via a wireless communication link identifying the product about which evaluation information is to be communicated. The method further includes comparing an indication of the signal to data in the data store in response to match the indication with a portion of the data and communicating evaluation information between the wireless client device and the system.
摘要翻译：讨论了在具有数据存储的系统和无线客户端设备之间传递关于产品评估的信息的方法。该方法包括经由无线通信链路从客户端设备接收表示可听见的指示的信号，该无线通信链路标识关于哪个评估信息要传达的产品。所述方法还包括将所述信号的指示与所述数据存储中的数据进行比较，以响应所述指示与所述数据的一部分匹配并在所述无线客户端设备与所述系统之间传送评估信息。

7. 发明申请

US20070143110A1 Time-anchored posterior indexing of speech 有权
标题翻译：时间锚定的后向索引语音
公开(公告)号：US20070143110A1
公开(公告)日：2007-06-21
申请号：US11300735
申请日：2005-12-15
申请人： Alejandro Acero , Asela Gunawardana , Ciprian Chelba , Erik Selberg , Frank Torsten Seide , Patrick Nguyen , Roger Yu
发明人： Alejandro Acero , Asela Gunawardana , Ciprian Chelba , Erik Selberg , Frank Torsten Seide , Patrick Nguyen , Roger Yu
IPC分类号： G10L15/04
CPC分类号： G10L15/08 , G10L15/05
摘要： A computer-implemented method of indexing a speech lattice for search of audio corresponding to the speech lattice is provided. The method includes identifying at least two speech recognition hypotheses for a word which have time ranges satisfying a criteria. The method further includes merging the at least two speech recognition hypotheses to generate a merged speech recognition hypothesis for the word.
摘要翻译：提供了一种用于索引用于搜索与语音格子相对应的音频的语音格子的计算机实现的方法。该方法包括识别具有满足标准的时间范围的单词的至少两个语音识别假设。该方法还包括合并至少两个语音识别假设以产生该单词的合并语音识别假设。

8. 发明授权

US07926485B2 Medical ventilator with compressor heated exhalation filter 有权
标题翻译：医用呼吸机带压缩机加热呼气过滤器
公开(公告)号：US07926485B2
公开(公告)日：2011-04-19
申请号：US12323792
申请日：2008-11-26
申请人： Patrick Nguyen , Gardner J. Kimm , Steve Han , Mabini M. Arcilla
发明人： Patrick Nguyen , Gardner J. Kimm , Steve Han , Mabini M. Arcilla
IPC分类号： F24J3/00 , A62B7/10 , A62B23/02
CPC分类号： A61M16/1055 , A61M16/0057 , A61M16/0858 , A61M16/1065 , A61M16/204 , A61M16/205 , A61M2016/0027 , A61M2016/0039 , A61M2016/0042 , A61M2205/3368 , A61M2205/3633 , A61M2205/3666 , A61M2205/42
摘要： A medical ventilator includes a pressure generator for increasing a pressure of gas that produces heat during the operation thereof. A heat sink spaced from the pressure generator is provided for absorbing heat from the pressure generator. A bacteria filter requiring heating in excess of an ambient temperature for the effective operation thereof is coupled in thermal communication with the heat sink. A heat pipe is coupled in thermal communication with the heat sink and the pressure generator for conveying at least part of heat produced by the pressure generator to the bacteria filter via the heat sink.
摘要翻译：医用呼吸机包括用于在其操作期间增加产生热量的气体的压力的压力发生器。提供与压力发生器间隔开的散热器，用于从压力发生器吸收热量。需要加热超过环境温度以用于其有效操作的细菌过滤器与散热器热连通地耦合。热管与散热器和压力发生器热连通地耦合，用于将由压力发生器产生的至少一部分热量经由散热器传送到细菌过滤器。

9. 发明授权

US07328154B2 Bubble splitting for compact acoustic modeling 有权
标题翻译：气泡分裂用于紧凑的声学建模
公开(公告)号：US07328154B2
公开(公告)日：2008-02-05
申请号：US10639974
申请日：2003-08-13
申请人： Ambroise Mutel , Patrick Nguyen , Luca Rigazio
发明人： Ambroise Mutel , Patrick Nguyen , Luca Rigazio
IPC分类号： G10L15/00
CPC分类号： G10L15/063 , G10L15/144 , G10L2015/0631 , G10L2015/0638
摘要： An improved method is provided for constructing compact acoustic models for use in a speech recognizer. The method includes: partitioning speech data from a plurality of training speakers according to at least one speech related criteria (i.e., vocal tract length); grouping together the partitioned speech data from training speakers having a similar speech characteristic; and training an acoustic bubble model for each group using the speech data within the group.
摘要翻译：提供了一种用于构建用于语音识别器中的紧凑声学模型的改进方法。该方法包括：根据至少一个语音相关标准（即，声道长度）来分割来自多个训练说话者的语音数据; 将具有类似语音特征的训练说话者的分割语音数据分组在一起; 并使用组内的语音数据为每个组训练声音气泡模型。

10. 发明申请

US20070255566A1 Multi-slot dialog systems and methods 有权
标题翻译：多槽对话系统和方法
公开(公告)号：US20070255566A1
公开(公告)日：2007-11-01
申请号：US11787763
申请日：2007-04-17
申请人： Patrick Nguyen , Jesus Lopez-Amaro , Amit Desai , Adeeb Shana'a
发明人： Patrick Nguyen , Jesus Lopez-Amaro , Amit Desai , Adeeb Shana'a
IPC分类号： G10L15/00
CPC分类号： H04M3/4936 , G10L15/22
摘要： Systems and methods for constructing a series of interactions with a user to collect multiple pieces of related information for the purpose of accomplishing a specific goal or topic (a multi-slot dialog) using a component-based approach are disclosed. The method generally includes outputting a primary header prompt to elicit values for slots in a segment from the user, receiving a primary user response containing a value for each slot in at least a subset of the slots in the segment, processing the primary user response to determine at least one possible recognition value for each slot contained in the primary user response, filling each slot contained in the primary user response with a matched value selected from the corresponding possible recognition values, and repeating the outputting, receiving, processing and filling for any unfilled slots in the segment until all slots in the segment of slots are filled.
摘要翻译：公开了使用基于组件的方法来构建与用户进行一系列交互以收集多条相关信息以用于实现特定目标或主题（多时隙对话）的目的的系统和方法。该方法通常包括输出主标题提示以从用户中引出段中的时隙的值，接收包含段中的时隙的至少一个子集中的每个时隙的值的主用户响应，处理主用户响应确定主用户响应中包含的每个时隙的至少一个可能的识别值，用从相应的可能识别值中选择的匹配值填充主用户响应中包含的每个时隙，并重复输出，接收，处理和填充任何段中的未填充插槽，直到插槽段中的所有插槽都被填充为止。

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