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

US06687672B2 Methods and apparatus for blind channel estimation based upon speech correlation structure 有权
标题翻译：基于语音相关结构的盲信道估计方法与装置
公开(公告)号：US06687672B2
公开(公告)日：2004-02-03
申请号：US10099428
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： G10L1508
CPC分类号： G10L21/0208
摘要： Methods and apparatus for blind channel estimation of a speech signal corrupted by a communication channel are provided. One method includes converting a noisy speech signal into either a cepstral representation or a log-spectral representation; estimating a correlation of the representation of the noisy speech signal; determining an average of the noisy speech signal; constructing and solving, subject to a minimization constraint, a system of linear equations utilizing a correlation structure of a clean speech training signal, the correlation of the representation of the noisy speech signal, and the average of the noisy speech signal; and selecting a sign of the solution of the system of linear equations to estimate an average clean speech signal in a processing window.
摘要翻译：提供了由通信信道损坏的语音信号的盲信道估计的方法和装置。一种方法包括将噪声语音信号转换成倒谱表示或对数谱表示; 估计噪声语音信号的表示的相关性; 确定噪声语音信号的平均值; 利用最小化约束，构建和求解利用清晰语音训练信号的相关结构，噪声语音信号的表示与噪声语音信号的平均值的相关性的线性方程组; 以及选择线性方程式的解的符号来估计处理窗口中的平均清洁语音信号。

32. 发明授权

US06205426B1 Unsupervised speech model adaptation using reliable information among N-best strings 失效
标题翻译：无人监督的语音模型适应使用N最佳字符串中的可靠信息
公开(公告)号：US06205426B1
公开(公告)日：2001-03-20
申请号：US09237170
申请日：1999-01-25
申请人： Patrick Nguyen , Philippe Gelin , Jean-Claude Junqua
发明人： Patrick Nguyen , Philippe Gelin , Jean-Claude Junqua
IPC分类号： G10L1514
CPC分类号： G10L15/065
摘要： The system performs unsupervised speech model adaptation using the recognizer to generate the N-best solutions for an input utterance. Each of these N-best solutions is tested by a reliable information extraction process. Reliable information is extracted by a weighting technique based on likelihood scores generated by the recognizer, or by a non-linear thresholding function. The system may be used in a single pass implementation or iteratively in a multi-pass implementation.
摘要翻译：该系统使用识别器执行无监督的语音模型自适应，以产生用于输入语音的N最佳解。这些N最佳解决方案中的每一个都通过可靠的信息提取过程进行测试。通过基于由识别器生成的似然分数的加权技术或非线性阈值函数来提取可靠信息。该系统可以在单遍实现中或在多遍实现中迭代地使用。

33. 发明申请

US20120215630A1 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：US20120215630A1
公开(公告)日：2012-08-23
申请号：US13459435
申请日：2012-04-30
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： G06Q30/02
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。

34. 发明授权

US07988861B2 Materials based on tangled nanotubes or nanofibres, preparation method thereof and use of same 有权
标题翻译：基于缠结纳米管或纳米纤维的材料，其制备方法和用途
公开(公告)号：US07988861B2
公开(公告)日：2011-08-02
申请号：US11883644
申请日：2006-02-01
申请人： Cuong Pham-Huu , Marc-Jacques Ledoux , Dominique Begin , Patrick Nguyen , Julien Amadou , Jean-Philippe Tessonnier
发明人： Cuong Pham-Huu , Marc-Jacques Ledoux , Dominique Begin , Patrick Nguyen , Julien Amadou , Jean-Philippe Tessonnier
IPC分类号： C02F1/78
CPC分类号： B82Y40/00 , B01J20/20 , B01J20/205 , B01J21/185 , B01J23/745 , B82Y30/00 , C01B32/162 , C01B2202/36 , C02F1/283 , C02F2101/32 , C02F2305/08 , C04B35/52 , C04B35/83 , C04B2235/5288 , C04B2235/5409 , C04B2235/77 , D01F9/1271
摘要： A method of preparing a solid material based on tangled nanotubes and/or nanofibers, includes a step of growing carbon nanofibers and/or nanotubes with restraint in a contained reactor; and the materials thus obtained. The different uses of the materials are also disclosed.
摘要翻译：基于缠结的纳米管和/或纳米纤维制备固体材料的方法包括在所含的反应器中生长碳纳米纤维和/或纳米管的步骤; 和由此获得的材料。还公开了材料的不同用途。

35. 发明申请

US20090241960A1 DUAL HIGH AND LOW PRESSURE BREATHING SYSTEM 审中-公开
标题翻译：双高低压呼吸系统
公开(公告)号：US20090241960A1
公开(公告)日：2009-10-01
申请号：US12060584
申请日：2008-04-01
申请人： Stephen Tunnell , Patrick Nguyen , Kosuke Inoue
发明人： Stephen Tunnell , Patrick Nguyen , Kosuke Inoue
IPC分类号： A62B9/02
CPC分类号： A62B9/02 , A61M16/0066 , A61M16/0069 , A61M16/101 , A61M16/12 , A61M16/125 , A61M16/20 , A61M16/204 , A61M2016/0027 , A61M2016/0039 , A61M2202/0208 , A61M2202/03 , A61M2202/0007
摘要： A breathing system allows a single valve and corresponding control system to utilize either high or low pressure gas input and control the delivery of gas to a patient in a manner independent of the gas pressure level. Some such systems include a blower that provides gas with low pressure, a high pressure inlet port, a force balance valve or similar that will regulate the high pressure to work in the low pressure system, and a proportional valve assembly with a unitary control system that will allow for efficient ventilation operations regardless of gas source. Some such systems are capable of seamless transition from low to high pressure and from high to low pressure gas sources, as well as independent operation while either source serves as an input.
摘要翻译：呼吸系统允许单个阀和相应的控制系统利用高压或低压气体输入并且以独立于气体压力水平的方式控制向患者输送气体。一些这样的系统包括提供低压气体的鼓风机，高压入口，力平衡阀或类似物，其将调节在低压系统中工作的高压;以及具有单一控制系统的比例阀组件，将允许有效的通风操作，无论气源如何。一些这样的系统能够从低压到高压以及从高压到低压气源无缝地转换，以及独立运行，而任一个源都用作输入。

36. 发明申请

US20080300872A1 SCALABLE SUMMARIES OF AUDIO OR VISUAL CONTENT 审中-公开
标题翻译：音频或视觉内容的可比性概要
公开(公告)号：US20080300872A1
公开(公告)日：2008-12-04
申请号：US11756059
申请日：2007-05-31
申请人： Sumit Basu , Surabhi Gupta , John C. Platt , Patrick Nguyen , Milind V. Mahajan
发明人： Sumit Basu , Surabhi Gupta , John C. Platt , Patrick Nguyen , Milind V. Mahajan
IPC分类号： G10L15/26
CPC分类号： G10L15/26 , G06F16/40 , G06F16/64 , G06F16/685 , G06F16/739 , G06F16/7844 , H04N7/147
摘要： Providing for browsing a summary of content formed of keywords that can scale to a user-defined level of detail is disclosed herein. Components of a system can include a summarization component that extracts keywords related to the content and associates the keywords with portions thereof, and a zooming component that displays a number of keywords based on a keyword/keyphrase relevance rank and a zoom factor. Additionally, a speech to text component can translate speech associated with the content into text, wherein the keywords are extracted from the translated text. Consequently, the claimed subject matter can present a variable hierarchy of keywords to form a scalable summary of such recorded content.
摘要翻译：本文公开了提供浏览由缩放到用户定义的细节级别的关键字形成的内容的摘要。系统的组件可以包括摘要组件，其提取与内容相关的关键词并将关键字与其部分相关联，以及缩放组件，其基于关键字/关键短语相关性等级和缩放因子显示多个关键字。此外，对文本组件的语音可以将与内容相关联的语音翻译为文本，其中从翻译的文本中提取关键字。因此，所要求保护的主题可以呈现关键词的可变层级以形成这种记录内容的可伸缩摘要。

37. 发明申请

US20080177536A1 A/V CONTENT EDITING 审中-公开
标题翻译： A / V内容编辑
公开(公告)号：US20080177536A1
公开(公告)日：2008-07-24
申请号：US11626726
申请日：2007-01-24
申请人： Adil Sherwani , Christopher Weare , Patrick Nguyen , Milind Mahajan , Alex Acero , Manuel Clement , Patrick Nelson
发明人： Adil Sherwani , Christopher Weare , Patrick Nguyen , Milind Mahajan , Alex Acero , Manuel Clement , Patrick Nelson
IPC分类号： G10L15/26
CPC分类号： G11B27/10 , G06F16/685 , G10L15/26 , G11B27/034
摘要： A/V content creation, editing and publishing is disclosed. Speech recognition can be performed on the A/V content to identify words therein and form a transcript of the words. The transcript can be aligned with the associated A/V content and displayed to allow selective editing of the transcript and associated A/V content. Keywords and a summary for the transcript can also be identified for use in publishing the A/V content.
摘要翻译：披露了A / V内容创作，编辑和出版。可以对A / V内容执行语音识别，以识别其中的单词并形成单词的抄本。誊本可以与相关的A / V内容对齐，并显示为允许选择性地编辑抄本和相关的A / V内容。关键词和抄本的摘要也可以用于发布A / V内容。

38. 发明授权

US06970820B2 Voice personalization of speech synthesizer 有权
标题翻译：语音合成器的语音个性化
公开(公告)号：US06970820B2
公开(公告)日：2005-11-29
申请号：US09792928
申请日：2001-02-26
申请人： Jean-Claude Junqua , Florent Perronnin , Roland Kuhn , Patrick Nguyen
发明人： Jean-Claude Junqua , Florent Perronnin , Roland Kuhn , Patrick Nguyen
IPC分类号： G10L13/08 , G10L13/02 , G10L13/04 , G10L13/06 , G10L21/00 , G10L13/00
CPC分类号： G10L13/04 , G10L2021/0135
摘要： The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters. To adapt the parameters with a small amount of enrollment data, an eigenspace is constructed and used to constrain the position of the new speaker so that context independent parameters not provided by the new speaker may be estimated.
摘要翻译：语音合成器被个性化以发音或模仿单个扬声器的语音特征。单个扬声器提供一定数量的登记数据，其可以从短语言中提取，并且系统将基本合成参数修改为更接近于新说话者的参考数据。更具体地，合成参数可以被分解为与扬声器相关的参数，诸如与上下文无关的参数，以及与扬声器无关的参数，诸如与上下文相关的参数。使用来自新扬声器的注册数据来调整与扬声器相关的参数。在适应之后，将扬声器依赖参数与扬声器独立参数组合以提供一组个性化合成参数。为了使参数具有少量的注册数据，构造本征空间并用于约束新的说话者的位置，以便可以估计不能由新发言者提供的上下文独立参数。

39. 发明申请

US20050159952A1 Pattern matching for large vocabulary speech recognition with packed distribution and localized trellis access 审中-公开
标题翻译：用于大量词汇语音识别的模式匹配，具有打包分发和本地化网格访问
公开(公告)号：US20050159952A1
公开(公告)日：2005-07-21
申请号：US10512354
申请日：2003-03-19
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
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 (20). Similarity measures for acoustic feature vectors (54) are determined in groups that are then buffered into cache memory (59). To further reduce computational processing, the acoustic data may be partitioned amongst a plurality of processing nodes (66, 67, 68). In addition, a priori knowledge of the spoken order may be used to establish the access order (124) used to copy records from the main speech parameter table (120, 200) into a sub-table (130, 204). The sub-table is processed such that the entries are in contiguous memory locations (206) and sorted according to the processing order (208). The speech processing algorithm is then directed to operate upon the sub-table (210) which causes the processor to load the sub-table into high speed cache memory (104, 212).
摘要翻译：提供了一种用于改进具有多个声学模型（20）的语音识别系统中的模式匹配的方法。以随后缓冲到高速缓存存储器（59）中的组确定声学特征向量（54）的相似性度量。为了进一步减少计算处理，可以在多个处理节点（66,67,68）之间划分声学数据。此外，可以使用口语顺序的先验知识来建立用于将记录从主语音参数表（120,200）复制到子表（130,204）中的访问顺序（124）。处理子表使得条目在连续存储器位置（206）中并根据处理顺序（208）进行排序。语音处理算法随后被引导以对子表（210）进行操作，这使得处理器将子表加载到高速缓存存储器（104,212）中。

40. 发明授权

US06915259B2 Speaker and environment adaptation based on linear separation of variability sources 有权
标题翻译：基于可变性来源线性分离的扬声器和环境适应
公开(公告)号：US06915259B2
公开(公告)日：2005-07-05
申请号：US09864838
申请日：2001-05-24
申请人： Luca Rigazio , Patrick Nguyen , David Kryze , Jean-Claude Junqua
发明人： Luca Rigazio , Patrick Nguyen , David Kryze , Jean-Claude Junqua
IPC分类号： G10L15/06 , G10L21/02
CPC分类号： G10L15/07 , G10L21/0208
摘要： Linear approximation of the background noise is applied after feature extraction and prior to speaker adaptation to allow the speaker adaptation system to adapt the speech models to the enrolling user without distortion from background noise. The linear approximation is applied in the feature domain, such as in the cepstral domain. Any adaptation technique that is commutative in the feature domain may be used.
摘要翻译：背景噪声的线性近似在特征提取之后并且在说话者适配之前被应用，以允许扬声器适配系统将语音模型适应于登记用户，而不会从背景噪声失真。线性近似应用于特征域，如倒谱域。可以使用在特征域中可交换的任何适配技术。

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