公开(公告)号：US20050063083A1

公开(公告)日：2005-03-24

申请号：US10692779

申请日：2003-10-24

申请人： Scott Dart ,  Bradley Gibson ,  Christopher Evans ,  Paul Hellyar ,  Alexander Vaschillo ,  John Platt ,  Steve Glenner ,  Nathaniel Ballou

发明人： Scott Dart ,  Bradley Gibson ,  Christopher Evans ,  Paul Hellyar ,  Alexander Vaschillo ,  John Platt ,  Steve Glenner ,  Nathaniel Ballou

IPC分类号： G06F7/00 ,  G06F12/00 ,  G06F13/00 ,  G06F17/00 ,  G11B5/00

CPC分类号： G06F17/30595 ,  G06F17/30244 ,  Y10S707/99935 ,  Y10S707/99943 ,  Y10S707/99944 ,  Y10S707/99945

摘要： In an Item-based system, Images (e.g., JPEG, TIFF, bitmap, and so on) are treated as core platform objects (“Image Items” or, more simply, “Images”) and exist in an “Image Schema” that provides an extensible representation of an Image in the system-that is, the characteristics of an Image and how that Image relates to other Items (including but not limited to other Images) in the system. To this end, the Image Schema defines the properties, behaviors, and relationships for Images in the system, and the Schema also enforces rules about Images, for example, what data specific Images must contain, what data specific Images may optionally contain, how specific Images can be extended, and so on and so forth.

摘要翻译： 在基于项目的系统中，将图像（例如，JPEG，TIFF，位图等）视为核心平台对象（“图像项目”，或更简单地说，“图像”），并存在于“图像模式”中 在系统中提供图像的可扩展表示，即图像的特征以及该图像与系统中的其他项目（包括但不限于其他图像）相关。 为此，图像模式定义了系统中图像的属性，行为和关系，并且模式还强制执行关于图像的规则，例如，特定图像必须包含哪些数据，特定图像可能包含哪些数据，具体如何 图像可以被扩展，依此类推。

公开(公告)号：US20060047584A1

公开(公告)日：2006-03-02

申请号：US10931889

申请日：2004-09-01

申请人： Alexander Vaschillo ,  Bradley Gibson ,  Christopher Evans ,  John Platt ,  Nathaniel Ballou ,  Paul Hellyar ,  Scott Dart ,  Steve Glenner

发明人： Alexander Vaschillo ,  Bradley Gibson ,  Christopher Evans ,  John Platt ,  Nathaniel Ballou ,  Paul Hellyar ,  Scott Dart ,  Steve Glenner

IPC分类号： G06F17/60

CPC分类号： G06F17/30277 ,  G06Q30/0625 ,  G06Q30/0641

摘要： A system and method for presenting images and related items to a user. A digital image from a data store is assessed, and a portion of the image is defined as a region of interest. Properties are associated with this defined region, and these properties are utilized to infer relationships between the region of interest and related items in the data store. Optionally, a user input indicating a desire to view related content may be received and such content may be presented to the user.

摘要翻译： 一种用于向用户呈现图像和相关物品的系统和方法。 评估来自数据存储的数字图像，并且将图像的一部分定义为感兴趣的区域。 属性与此定义的区域相关联，并且这些属性用于推断感兴趣区域和数据存储区中相关项目之间的关系。 可选地，可以接收指示观看相关内容的用户输入，并且可以向用户呈现这样的内容。

公开(公告)号：US08738354B2

公开(公告)日：2014-05-27

申请号：US12488422

申请日：2009-06-19

申请人： John Platt ,  Ilya Sutskever

发明人： John Platt ,  Ilya Sutskever

IPC分类号： G06F17/28 ,  G06F17/20

CPC分类号： G06F17/28 ,  G06N3/0454

摘要： A method of creating translingual text representations takes in documents in a first language and in a second language and creates a matrix using the words in the documents to represent which words are present in which language. An algorithm is applied to each matrix such that like documents are placed close to each other and unlike documents are moved far from each other.

摘要翻译： 创建跨文本表示的方法以第一语言和第二语言获取文档，并且使用文档中的单词创建矩阵来表示以哪种语言存在哪些单词。 一种算法被应用于每个矩阵，使得类似的文档被放置得彼此靠近，并且不同的文档彼此远离地移动。

公开(公告)号：US08416946B2

公开(公告)日：2013-04-09

申请号：US12890075

申请日：2010-09-24

申请人： Amit Chhetri ,  Arungunram Surendran ,  Jack Stokes ,  John Platt

发明人： Amit Chhetri ,  Arungunram Surendran ,  Jack Stokes ,  John Platt

IPC分类号： H04M9/08

CPC分类号： H04M9/082

摘要： A regression-based residual echo suppression (RES) system and process for suppressing the portion of the microphone signal corresponding to a playback of a speaker audio signal that was not suppressed by an acoustic echo canceller (AEC). In general, a prescribed regression technique is used between a prescribed spectral attribute of multiple past and present, fixed-length, periods (e.g., frames) of the speaker signal and the same spectral attribute of a current period (e.g., frame) of the echo residual in the output of the AEC. This automatically takes into consideration the correlation between the time periods of the speaker signal. The parameters of the regression can be easily tracked using adaptive methods. Multiple applications of RES can be used to produce better results and this system and process can be applied to stereo-RES as well.

摘要翻译： 基于回归的残差回波抑制（RES）系统和用于抑制对应于未被声学回声消除器（AEC）抑制的扬声器音频信号的重放的麦克风信号的部分的处理。 通常，在多个过去和现在，固定长度的扬声器信号的周期（例如，帧）和当前周期（例如，帧）的相同频谱属性之间使用规定的回归技术 AEC输出中的回波残差。 这自动考虑了扬声器信号的时间段之间的相关性。 可以使用自适应方法轻松跟踪回归的参数。 RES的多个应用可以用于产生更好的结果，并且该系统和过程也可以应用于立体声RES。

公开(公告)号：US08290181B2

公开(公告)日：2012-10-16

申请号：US11084608

申请日：2005-03-19

申请人： Jack W. Stokes, III ,  John Platt ,  David Alan Stevens

发明人： Jack W. Stokes, III ,  John Platt ,  David Alan Stevens

IPC分类号： H03G3/00 ,  H03G9/00

CPC分类号： H04R3/005 ,  H03G3/301 ,  H03G3/3089 ,  H04R3/02 ,  H04R2410/00 ,  H04R2430/01

摘要： A system level automatic gain control (“System AGC”) automatically initializes and controls analog microphone gain in an environment where multiple independent applications simultaneously receive an input from a single analog microphone or microphone array. In one embodiment, the System AGC also prevents those applications from acting to separately control the gain by intercepting external gain control commands and responding to the corresponding application with a corresponding digital gain applied to the input signal from the microphone. Consequently, the System AGC avoids problems relating to oscillations and instability in the microphone gain resulting from multiple applications trying to simultaneously control the gain while preventing each application from adversely affecting the quality of another application's audio capture signal. Further, in one embodiment, the System AGC also acts to maximize the signal to noise (SNR) ratio of the microphone without introducing clipping as a function of a sampled background environment.

摘要翻译： 在多个独立应用程序同时从单个模拟麦克风或麦克风阵列接收输入的环境中，系统级自动增益控制（系统AGC）自动初始化和控制模拟麦克风增益。 在一个实施例中，系统AGC还防止这些应用通过截取外部增益控制命令来单独地控制增益，并且以对应于来自麦克风的输入信号的相应数字增益作出响应。 因此，系统AGC避免了与多个应用程序尝试同时控制增益相关的麦克风增益的振荡和不稳定性问题，同时防止每个应用程序不利地影响另一应用程序的音频捕获信号的质量。 此外，在一个实施例中，系统AGC还用于使麦克风的信噪比（SNR）最大化，而不会引入作为采样的背景环境的函数的削波。

公开(公告)号：US20100324883A1

公开(公告)日：2010-12-23

申请号：US12488422

申请日：2009-06-19

申请人： John Platt ,  Ilya Sutskever

发明人： John Platt ,  Ilya Sutskever

IPC分类号： G06F17/28 ,  G06N3/02 ,  G06F15/18

CPC分类号： G06F17/28 ,  G06N3/0454

摘要： A method of creating translingual text representations takes in documents in a first language and in a second language and creates a matrix using the words in the documents to represent which words are present in which language. An algorithm is applied to each matrix such that like documents are placed close to each other and unlike documents are moved far from each other.

摘要翻译： 创建跨文本表示的方法以第一语言和第二语言获取文档，并且使用文档中的单词创建矩阵来表示以哪种语言存在哪些单词。 一种算法被应用于每个矩阵，使得类似的文档被放置得彼此靠近，并且不同的文档彼此远离地移动。

公开(公告)号：US20070005341A1

公开(公告)日：2007-01-04

申请号：US11170989

申请日：2005-06-30

申请人： Christopher Burges ,  John Platt

发明人： Christopher Burges ,  John Platt

IPC分类号： G06F17/27

CPC分类号： G06F17/3071

摘要： A general probabilistic formulation referred to as ‘Conditional Harmonic Mixing’ is provided, in which links between classification nodes are directed, a conditional probability matrix is associated with each link, and where the numbers of classes can vary from node to node. A posterior class probability at each node is updated by minimizing a divergence between its distribution and that predicted by its neighbors. For arbitrary graphs, as long as each unlabeled point is reachable from at least one training point, a solution generally always exists, is unique, and can be found by solving a sparse linear system iteratively. In one aspect, an automated data classification system is provided. The system includes a data set having at least one labeled category node in the data set. A semi-supervised learning component employs directed arcs to determine the label of at least one other unlabeled category node in the data set.

摘要翻译： 提供了称为“条件谐波混合”的一般概率公式，其中分类节点之间的链接被引导，条件概率矩阵与每个链路相关联，并且类的数量可以在节点之间变化。 通过最小化其分布与其邻居预测的分布之间的差异来更新每个节点处的后级概率。 对于任意图，只要每个未标记的点从至少一个训练点到达，则通常总是存在的解是唯一的，并且可以通过迭代地求解稀疏线性系统来找到。 一方面，提供了一种自动数据分类系统。 该系统包括在数据集中具有至少一个标记类别节点的数据集。 半监督学习组件使用有向弧来确定数据集中至少一个其他未标记类别节点的标签。

公开(公告)号：US20060217968A1

公开(公告)日：2006-09-28

申请号：US11422862

申请日：2006-06-07

申请人： Chris Burges ,  John Platt

发明人： Chris Burges ,  John Platt

IPC分类号： G10L19/14

CPC分类号： G06K9/4647 ,  G06K9/6232 ,  G10L15/02 ,  G10L15/20

摘要： Extracting features from signals for use in classification, retrieval, or identification of data represented by those signals uses a “Distortion Discriminant Analysis” (DDA) of a set of training signals to define parameters of a signal feature extractor. The signal feature extractor takes signals having one or more dimensions with a temporal or spatial structure, applies an oriented principal component analysis (OPCA) to limited regions of the signal, aggregates the output of multiple OPCAs that are spatially or temporally adjacent, and applies OPCA to the aggregate. The steps of aggregating adjacent OPCA outputs and applying OPCA to the aggregated values are performed one or more times for extracting low-dimensional noise-robust features from signals, including audio signals, images, video data, or any other time or frequency domain signal. Such extracted features are useful for many tasks, including automatic authentication or identification of particular signals, or particular elements within such signals.

摘要翻译： 从用于分类，检索或识别由这些信号表示的数据的信号中提取特征使用一组训练信号的“失真判别分析”（DDA）来定义信号特征提取器的参数。 信号特征提取器采用具有时间或空间结构的一个或多个维度的信号，将定向主成分分析（OPCA）应用于信号的有限区域，聚合空间或时间相邻的多个OPCA的输出，并应用OPCA 到总计。 执行聚合相邻OPCA输出并将OPCA应用于聚合值的步骤一次或多次，用于从包括音频信号，图像，视频数据或任何其他时间或频域信号的信号中提取低维噪声鲁棒特征。 这些提取的特征对于许多任务是有用的，包括特定信号的自动认证或识别，或这些信号内的特定元件。

公开(公告)号：US20060210096A1

公开(公告)日：2006-09-21

申请号：US11084608

申请日：2005-03-19

申请人： Jack Stokes ,  John Platt ,  David Stevens

发明人： Jack Stokes ,  John Platt ,  David Stevens

IPC分类号： H03G3/00 ,  H03G9/00

CPC分类号： H04R3/005 ,  H03G3/301 ,  H03G3/3089 ,  H04R3/02 ,  H04R2410/00 ,  H04R2430/01

摘要： A system level automatic gain control (“System AGC”) automatically initializes and controls analog microphone gain in an environment where multiple independent applications simultaneously receive an input from a single analog microphone or microphone array. In one embodiment, the System AGC also prevents those applications from acting to separately control the gain by intercepting external gain control commands and responding to the corresponding application with a corresponding digital gain applied to the input signal from the microphone. Consequently, the System AGC avoids problems relating to oscillations and instability in the microphone gain resulting from multiple applications trying to simultaneously control the gain while preventing each application from adversely affecting the quality of another application's audio capture signal. Further, in one embodiment, the System AGC also acts to maximize the signal to noise (SNR) ratio of the microphone without introducing clipping as a function of a sampled background environment.

摘要翻译： 系统级自动增益控制（“系统AGC”）在多个独立应用程序同时从单个模拟麦克风或麦克风阵列接收输入的环境中自动初始化和控制模拟麦克风增益。 在一个实施例中，系统AGC还防止这些应用通过截取外部增益控制命令来单独地控制增益，并且以对应于来自麦克风的输入信号的相应数字增益作出响应。 因此，系统AGC避免了与多个应用程序尝试同时控制增益相关的麦克风增益的振荡和不稳定性问题，同时防止每个应用程序不利地影响另一应用程序的音频捕获信号的质量。 此外，在一个实施例中，系统AGC还用于使麦克风的信噪比（SNR）最大化，而不会引入作为采样的背景环境的函数的削波。

公开(公告)号：US20060167874A1

公开(公告)日：2006-07-27

申请号：US11041557

申请日：2005-01-24

申请人： Luis von Ahn Arellano ,  Eric Brill ,  John Platt ,  Josh Benaloh

发明人： Luis von Ahn Arellano ,  Eric Brill ,  John Platt ,  Josh Benaloh

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30864 ,  Y10S707/99945 ,  Y10S707/99948

摘要： The subject invention provides a unique system and method that facilitates an interactive game-powered search engine that serve the purposes of both users who may be looking for information as well as game participants who may desire to earn some reward or level of enjoyment by playing the game. More specifically, the system and method provides feedback to a user based on the user's input string or a string derived therefrom. The feedback can be a response or answer to the user's input in the form of text, an image, audio or sound, video, and/or a URL that is provided by one or more game participants when there is some degree of consistency or agreement between the responses or when individual players have demonstrated good reliability in their responses.