专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US06901364B2 Focused language models for improved speech input of structured documents 有权
标题翻译：用于改进结构化文档语音输入的专注语言模型
公开(公告)号：US06901364B2
公开(公告)日：2005-05-31
申请号：US09951093
申请日：2001-09-13
申请人： Patrick Nguyen , Luca Rigazio , Jean-Claude Junqua
发明人： Patrick Nguyen , Luca Rigazio , Jean-Claude Junqua
IPC分类号： G10L15/18 , G10L15/28 , G10L15/26 , G06F17/20 , G10L21/00
CPC分类号： G10L15/1815 , G10L15/30
摘要： An e-mail message process is provided for use with a personal digital assistant which allows for the use of input speech messaging which is converted to text using a focused language model which is downloaded by a cellular phone connection to an Internet server which provides the focused language model based upon a topic for the intended e-mail message. The text that is generated from the input speech method can be summarized by the e-mail message processor and can be edited by the user. The generated e-mail message can then be transmitted again via cellular connection to an Internet e-mail server for transmitting the e-mail message to a recipient.
摘要翻译：提供电子邮件消息处理以与个人数字助理一起使用，该个人数字助理允许使用输入语音消息传送，其使用由通过蜂窝电话连接下载的聚焦语言模型转换为文本，该互联网服务器提供聚焦基于预期电子邮件的主题的语言模型。从输入语音方法生成的文本可以由电子邮件消息处理器来总结，并且可以由用户编辑。然后可以通过蜂窝连接再次将生成的电子邮件消息发送到Internet电子邮件服务器，以将电子邮件消息发送给接收者。

12. 发明授权

US06895376B2 Eigenvoice re-estimation technique of acoustic models for speech recognition, speaker identification and speaker verification 有权
标题翻译：用于语音识别，扬声器识别和说话人验证的声学模型的本征语重新估计技术
公开(公告)号：US06895376B2
公开(公告)日：2005-05-17
申请号：US09849174
申请日：2001-05-04
申请人： Florent Perronnin , Roland Kuhn , Patrick Nguyen , Jean-Claude Junqua
发明人： Florent Perronnin , Roland Kuhn , Patrick Nguyen , Jean-Claude Junqua
IPC分类号： G10L15/06 , G10L17/00
CPC分类号： G10L15/07 , G10L17/02
摘要： A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.
摘要翻译：在训练期间使用减小的维度本征语音分析技术来开发用于异音素的上下文相关的声学模型。执行重新估计过程以更强烈地分离语音模型的与扬声器相关的和与扬声器无关的组件。特定语音技术在运行时也用于新演讲者的演讲。该技术可以消除单个扬声器的特性，从而产生更普遍适用和强大的异音模型。在一个实施例中，本征语音技术用于识别每个说话者的质心，然后可以将其“减去”识别方程。

13. 发明授权

US06879954B2 Pattern matching for large vocabulary speech recognition systems 有权
标题翻译：大词汇语音识别系统的模式匹配
公开(公告)号：US06879954B2
公开(公告)日：2005-04-12
申请号：US10127184
申请日：2002-04-22
申请人： Patrick Nguyen , Luca Rigazio
发明人： Patrick Nguyen , Luca Rigazio
IPC分类号： G10L15/08 , G10L15/10 , G10L15/28 , G10L15/00 , G06F15/76
CPC分类号： G10L15/08 , G10L15/10 , G10L15/285 , G10L15/30 , G10L15/34
摘要： A method is provided for improving pattern matching in a speech recognition system having a plurality of acoustic models. The improved method includes: receiving continuous speech input; generating a sequence of acoustic feature vectors that represent temporal and spectral behavior of the speech input; loading a first group of acoustic feature vectors from the sequence of acoustic feature vectors into a memory workspace accessible to a processor; loading an acoustic model from the plurality of acoustic models into the memory workspace; and determining a similarity measure for each acoustic feature vector of the first group of acoustic feature vectors in relation to the acoustic model. Prior to retrieving another group of acoustic feature vectors, similarity measures are computed for the first group of acoustic feature vectors in relation to each of the acoustic models employed by the speech recognition system. In this way, the improved method reduces the number I/O operations associated with loading and unloading each acoustic model into memory.
摘要翻译：提供了一种用于改进具有多个声学模型的语音识别系统中的模式匹配的方法。改进的方法包括：接收连续语音输入; 产生表示语音输入的时间和频谱行为的声学特征向量序列; 将来自声学特征向量序列的第一组声学特征向量加载到可由处理器访问的存储器工作空间; 将来自所述多个声学模型的声学模型加载到所述存储器工作空间中; 以及针对声学模型确定第一组声学特征向量的每个声学特征向量的相似性度量。在检索另一组声学特征向量之前，相对于由语音识别系统采用的每个声学模型，针对第一组声学特征向量计算相似性度量。以这种方式，改进的方法减少了将每个声学模型加载和卸载到存储器中的数量I / O操作。

14. 发明授权

US06263309B1 Maximum likelihood method for finding an adapted speaker model in eigenvoice space 失效
标题翻译：在本征语音空间中找到适应的说话者模型的最大似然法
公开(公告)号：US06263309B1
公开(公告)日：2001-07-17
申请号：US09070054
申请日：1998-04-30
申请人： Patrick Nguyen , Roland Kuhn , Jean-Claude Junqua
发明人： Patrick Nguyen , Roland Kuhn , Jean-Claude Junqua
IPC分类号： G10L1508
CPC分类号： G10L15/07
摘要： A set of speaker dependent models is trained upon a comparatively large number of training speakers, one model per speaker, and model parameters are extracted in a predefined order to construct a set of supervectors, one per speaker. Principle component analysis is then performed on the set of supervectors to generate a set of eigenvectors that define an eigenvoice space. If desired, the number of vectors may be reduced to achieve data compression. Thereafter, a new speaker provides adaptation data from which a supervector is constructed by constraining this supervector to be in the eigenvoice space based on a maximum likelihood estimation. The resulting coefficients in the eigenspace of this new speaker may then be used to construct a new set of model parameters from which an adapted model is constructed for that speaker. Environmental adaptation may be performed by including environmental variations in the training data.
摘要翻译：一组扬声器依赖模型训练在相对较多数量的训练扬声器上，每个扬声器一个模型和模型参数以预定义的顺序提取，以构建一组超级矢量，每个扬声器一个。然后在一组超级矢量上执行原理分量分析，以生成一组定义本征语音空间的特征向量。如果需要，可以减少向量的数量以实现数据压缩。此后，新的说话者提供了通过基于最大似然估计将该超向量限制在本征语音空间中来构建超向量的适配数据。然后，可以使用这个新的说话者的本征空间中得到的系数来构建一组新的模型参数，从该模型参数构建适合于该说话者的适应模型。可以通过在训练数据中包括环境变化来执行环境适应。

15. 发明授权

US5345255A Actuator mechanism for a plotter carriage 失效
标题翻译：执行器机构用于绘图机
公开(公告)号：US5345255A
公开(公告)日：1994-09-06
申请号：US834970
申请日：1992-02-14
申请人： Patrick Nguyen , Brian C. Preston
发明人： Patrick Nguyen , Brian C. Preston
IPC分类号： G01D15/16 , B43L13/00
CPC分类号： G01D15/16
摘要： An actuator mechanism for a plotter carriage adaptable for use in either a pen plotter or a pencil plotter mode in which a coupler engages both a support for a pen holder and a support for a lead holder and a motor and an actuator arm coupled to the motor are provided for driving the coupler relative to a drawing media surface. An interlock and a sensor are provided to enable the motor, actuator arm and coupler to be coupled to a pencil actuator mechanism and to determine whether the plotter carriage is being used in a pen plotter or a pencil plotter mode.
摘要翻译：一种用于可适用于笔式绘图机或铅笔绘图仪模式的绘图机托架的致动器机构，其中耦合器与笔夹的支撑件和用于引线架的马达和马达的支撑件接合，以及耦合到马达的致动器臂被提供用于相对于牵引介质表面驱动联接器。提供互锁和传感器以使得电动机，致动器臂和联接器能够耦合到铅笔执行器机构并且确定绘图机托架是用在笔式绘图仪还是铅笔绘图仪模式中。

16. 发明申请

US20210080262A1 SELF-SEATING SYSTEM AND METHOD 有权
公开(公告)号：US20210080262A1
公开(公告)日：2021-03-18
申请号：US16568955
申请日：2019-09-12
申请人： Terrance J O'Shea , Patrick Nguyen , Tom E Pearson
发明人： Terrance J O'Shea , Patrick Nguyen , Tom E Pearson
IPC分类号： G01C21/20 , G06F3/0488 , H04W4/33 , H04W4/38
摘要： A self-seating system is described. The self-seating system includes a guest interface for communicating with an arriving guest information relating to a seating assignment and a processing device communicating with the guest interface. The self-seating system also includes more than one directional display providing guidance to the guest as to the location of their seating assignment. The directional displays is selectively activated and deactivated through communication and signaling by the processing device. The self-seating system further includes a seating sensor communicating with the processing device as to when a guest is seated at a particular location.

17. 发明申请

US20140194542A1 CATALYTIC PROCESS FOR THE CONVERSION OF A SYNTHESIS GAS TO HYDROCARBONS 有权
标题翻译：将合成气转化为烃类的催化方法
公开(公告)号：US20140194542A1
公开(公告)日：2014-07-10
申请号：US14123235
申请日：2012-05-31
申请人： Francis Luck , Charlotte Pham , Patrick Nguyen , Cuong Pham-Huu , Benoit De Tymowski
发明人： Francis Luck , Charlotte Pham , Patrick Nguyen , Cuong Pham-Huu , Benoit De Tymowski
IPC分类号： C07C1/04 , B01J27/224
CPC分类号： C07C1/044 , B01J21/06 , B01J23/745 , B01J23/75 , B01J23/78 , B01J23/83 , B01J23/8906 , B01J23/8913 , B01J27/22 , B01J27/224 , B01J35/002 , B01J35/1009 , B01J35/1038 , B01J35/1061 , B01J35/1066 , B01J37/0009 , B01J37/0201 , C07C1/0435 , C10G2/332 , C10G2300/1022 , C10G2300/703
摘要： Catalytic process for the partial conversion of a gaseous mixture containing carbon monoxide and hydrogen into a mixture of hydrocarbons, including bringing the said gaseous mixture into contact with a solid catalyst, the solid catalyst having a porous support with a composite material including SiC and a titanium carbide and/or a titanium oxide, and an active phase. The support is prepared in the form of grains, beads, or extrudates, or in the form of cylinders or sheets of cellular foam.
摘要翻译：用于将含有一氧化碳和氢气的气态混合物部分转化成烃混合物的催化方法，包括使所述气态混合物与固体催化剂接触，所述固体催化剂具有多孔载体，所述复合材料包括SiC和钛碳化物和/或氧化钛，以及活性相。载体以颗粒，珠粒或挤出物的形式制备，或以圆泡或细胞泡沫片的形式制备。

18. 发明申请

US20090240486A1 HMM ALIGNMENT FOR COMBINING TRANSLATION SYSTEMS 有权
标题翻译：用于组合翻译系统的HMM对齐
公开(公告)号：US20090240486A1
公开(公告)日：2009-09-24
申请号：US12147807
申请日：2008-06-27
申请人： Xiaodong He , Mei Yang , Jianfeng Gao , Patrick Nguyen
发明人： Xiaodong He , Mei Yang , Jianfeng Gao , Patrick Nguyen
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2818
摘要： A computing system configured to produce an optimized translation hypothesis of text input into the computing system. The computing system includes a plurality of translation machines. Each of the translation machines is configured to produce their own translation hypothesis from the same text. An optimization machine is connected to the plurality of translation machines. The optimization machine is configured to receive the translation hypotheses from the translation machines. The optimization machine is further configured to align, word-to-word, the hypotheses in the plurality of hypotheses by using a hidden Markov model.
摘要翻译：一种计算系统，被配置为产生文本输入到所述计算系统中的优化翻译假说。计算系统包括多个翻译机。每个翻译机被配置为从相同的文本产生他们自己的翻译假设。优化机连接到多台翻译机。优化机被配置为从翻译机接收翻译假说。优化机还被配置为通过使用隐马尔科夫模型来对齐单词到多个假设中的假设。

19. 发明申请

US20090199235A1 VIDEO CONTEXTUAL ADVERTISEMENTS USING SPEECH RECOGNITION 有权
标题翻译：使用语音识别的视频语境广告
公开(公告)号：US20090199235A1
公开(公告)日：2009-08-06
申请号：US12134214
申请日：2008-06-06
申请人： Arungunram C. Surendran , Patrick Nguyen , Milind V. Mahajan
发明人： Arungunram C. Surendran , Patrick Nguyen , Milind V. Mahajan
IPC分类号： H04N7/025 , G10L15/00
CPC分类号： H04N21/8405 , G06Q30/02 , G06Q30/0255 , G06Q30/0269 , G06Q30/0271 , G10L15/26 , H04N21/440236 , H04N21/4668 , H04N21/812
摘要： Embodiments of a computer-implemented advertisement display system are disclosed. In one embodiment, the system includes a speech recognition component that processes a video clip and produces a corresponding collection of speech recognition data indicative of an audio portion of the video clip. The system also includes a collection of advertising material. An advertisement selection component selects an advertisement from the collection of advertising material based on the corresponding collection of speech recognition data. The system also includes a display. An advertisement presentation component displays an indication of the selected advertisement on the display during a simultaneous display of the video clip.
摘要翻译：公开了一种计算机实现的广告显示系统的实施例。在一个实施例中，系统包括语音识别组件，其处理视频剪辑并产生指示视频剪辑的音频部分的语音识别数据的相应集合。该系统还包括一系列广告材料。广告选择组件基于相应的语音识别数据集合从广告素材的集合中选择广告。该系统还包括显示器。广告呈现组件在同时显示视频剪辑期间在显示器上显示所选广告的指示。

20. 发明授权

US07089182B2 Method and apparatus for feature domain joint channel and additive noise compensation 有权
公开(公告)号：US07089182B2
公开(公告)日：2006-08-08
申请号：US10099305
申请日：2002-03-15
申请人： Younes Souilmi , Luca Rigazio , Patrick Nguyen , Jean-Claude Junqua
发明人： Younes Souilmi , Luca Rigazio , Patrick Nguyen , Jean-Claude Junqua
IPC分类号： G10L15/20
CPC分类号： G10L15/20 , G10L15/02 , G10L15/063 , G10L21/0216
摘要： A method for performing noise adaptation of a target speech signal input to a speech recognition system, where the target speech signal contains both additive and convolutional noises. The method includes estimating an additive noise bias and a convolutional noise bias; in the target speech signal; and jointly compensating the target speech signal for the additive and convolutional noise biases in a feature domain.

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