公开(公告)号：US20090214052A1

公开(公告)日：2009-08-27

申请号：US12035439

申请日：2008-02-22

Applicant: Zicheng Liu ,  Philip Andrew Chou ,  Jacek Dmochowski

Inventor： Zicheng Liu ,  Philip Andrew Chou ,  Jacek Dmochowski

IPC: H04R3/00

CPC classification number: H04R27/00 ,  G10L21/0272

Abstract: A system that facilitates blind source separation in a distributed microphone meeting environment for improved teleconferencing. Input sensor (e.g., microphone) signals are transformed to the frequency-domain and independent component analysis is applied to compute estimates of frequency-domain processing matrices. Modified permutations of the processing matrices are obtained based upon a maximum magnitude based de-permutation scheme. Estimates of the plurality of source signals are provided based upon the modified frequency-domain processing matrices and input sensor signals.Optionally, segments during which the set of active sources is a subset of the set of all sources can be exploited to compute more accurate estimates of frequency-domain mixing matrices. Source activity detection can be applied to determine which speaker(s), if any, are active. Thereafter, a least squares post-processing of the frequency-domain independent components analysis outputs can be employed to adjust the estimates of the source signals based on source inactivity.

Abstract translation: 一种促进分布式麦克风会议环境中盲源分离的系统，用于改进电话会议。 输入传感器（例如麦克风）信号被变换到频域，并且应用独立分量分析来计算频域处理矩阵的估计。 基于最大幅度的去排列方案获得处理矩阵的修改排列。 基于改进的频域处理矩阵和输入传感器信号来提供多个源信号的估计。 可选地，可以利用其中该组活动源是所有源的集合的子集的段来计算频域混合矩阵的更准确的估计。 源活动检测可以应用于确定哪些扬声器（如果有）是活动的。 此后，可以采用频域独立分量分析输出的最小二乘后处理，以基于源不活动来调整源信号的估计。

公开(公告)号：US08144896B2

公开(公告)日：2012-03-27

申请号：US12035439

申请日：2008-02-22

Applicant: Zicheng Liu ,  Philip Andrew Chou ,  Jacek Dmochowski

Inventor： Zicheng Liu ,  Philip Andrew Chou ,  Jacek Dmochowski

IPC: H04B15/00

CPC classification number: H04R27/00 ,  G10L21/0272

Abstract: A system that facilitates blind source separation in a distributed microphone meeting environment for improved teleconferencing. Input sensor (e.g., microphone) signals are transformed to the frequency-domain and independent component analysis is applied to compute estimates of frequency-domain processing matrices. Modified permutations of the processing matrices are obtained based upon a maximum magnitude based de-permutation scheme. Estimates of the plurality of source signals are provided based upon the modified frequency-domain processing matrices and input sensor signals.Optionally, segments during which the set of active sources is a subset of the set of all sources can be exploited to compute more accurate estimates of frequency-domain mixing matrices. Source activity detection can be applied to determine which speaker(s), if any, are active. Thereafter, a least squares post-processing of the frequency-domain independent components analysis outputs can be employed to adjust the estimates of the source signals based on source inactivity.

Abstract translation: 一种促进分布式麦克风会议环境中盲源分离的系统，用于改进电话会议。 输入传感器（例如麦克风）信号被变换到频域，并且应用独立分量分析来计算频域处理矩阵的估计。 基于最大幅度的去排列方案获得处理矩阵的修改排列。 基于改进的频域处理矩阵和输入传感器信号来提供多个源信号的估计。 可选地，可以利用其中该组活动源是所有源的集合的子集的段来计算频域混合矩阵的更准确的估计。 源活动检测可以应用于确定哪些扬声器（如果有）是活动的。 此后，可以采用频域独立分量分析输出的最小二乘后处理，以基于源不活动来调整源信号的估计。

公开(公告)号：US20130294710A1

公开(公告)日：2013-11-07

申请号：US13463934

申请日：2012-05-04

Applicant: Philip Andrew Chou ,  Cha Zhang ,  Zhengyou Zhang ,  Shujie Liu

Inventor： Philip Andrew Chou ,  Cha Zhang ,  Zhengyou Zhang ,  Shujie Liu

IPC: G06K9/32

CPC classification number: G06K9/32 ,  G06T7/593

Abstract: A temporal information integration dis-occlusion system and method for using historical data to reconstruct a virtual view containing an occluded area. Embodiments of the system and method use temporal information of the scene captured previously to obtain a total history. This total history is warped onto information captured by a camera at a current time in order to help reconstruct the dis-occluded areas. The historical data (or frames) from the total history match only a portion of the frames contained in the captured information. This warping yields warped history information. Warping is performed by using one of two embodiments to match points in an estimation of the current information to points in the captured information. Next, regions of current information are split using a classifier. The warped history information and the captured information then are merged to obtain an estimate for the current information and the reconstructed virtual view.

Abstract translation: 一种用于使用历史数据重建包含遮挡区域的虚拟视图的时间信息整合遮挡系统和方法。 系统和方法的实施例使用先前捕获的场景的时间信息来获得总历史。 这个总历史在当前时间由相机拍摄的信息扭曲，以帮助重建被遮挡的区域。 来自总历史记录的历史数据（或帧）仅匹配捕获信息中包含的帧的一部分。 这种扭曲产生扭曲的历史信息。 通过使用两个实施例中的一个实现扭曲，以将当前信息的估计中的点与捕获的信息中的点进行匹配。 接下来，使用分类器分割当前信息的区域。 然后将翘曲的历史信息和捕获的信息合并，以获得当前信息和重建的虚拟视图的估计。

公开(公告)号：US08228824B2

公开(公告)日：2012-07-24

申请号：US11398817

申请日：2006-04-06

Applicant: David Milstein ,  David Howell ,  Kuansan Wang ,  Linda Criddle ,  Michael D Malueg ,  Philip Andrew Chou ,  Scott Forbes ,  Timothy M Moore

Inventor： David Milstein ,  David Howell ,  Kuansan Wang ,  Linda Criddle ,  Michael D Malueg ,  Philip Andrew Chou ,  Scott Forbes ,  Timothy M Moore

IPC: H04Q11/00

CPC classification number: H04L29/06027

Abstract: A method and system for processing contextual information relating to an exchange of a conversation over a communication channel is provided. Several users, and/or service providers are allowed to specify a set of rules relating to a conversation channel. Contextual information, including information relating to the specified set of rules and conditions of the users, is exchanged among the users and/or several service providers when one user requests to initiate a communication channel. The received contextual information is processed to extract a set of rules and the current conditions of users. If the current conditions of the users satisfy the set of rules, a corresponding communication channel is established among the users. However, additional contextual information may be received and processed whenever there is a change in the contextual information during the conversation. Appropriate actions to the existing communication channel may be determined based on the changes.

Abstract translation: 提供了一种用于处理与通信通道上的对话交换有关的上下文信息的方法和系统。 允许几个用户和/或服务提供商指定与会话信道相关的一组规则。 当一个用户请求启动通信信道时，在用户和/或若干服务提供商之间交换包括与指定的一组规则和条件有关的信息的上下文信息。 处理收到的上下文信息以提取一组规则和用户的当前条件。 如果用户的当前条件满足规则集，则在用户之间建立相应的通信信道。 然而，只要在会话期间上下文信息发生变化，就可以接收和处理附加的上下文信息。 可以基于变化来确定对现有通信信道的适当动作。

公开(公告)号：US5689620A

公开(公告)日：1997-11-18

申请号：US431223

申请日：1995-04-28

Applicant: Gary E. Kopec ,  Philip Andrew Chou ,  Leslie T. Niles

Inventor： Gary E. Kopec ,  Philip Andrew Chou ,  Leslie T. Niles

IPC: G06K9/66 ,  G06K9/62 ,  G06T1/40 ,  G06K9/00

CPC classification number: G06K9/6256

Abstract: A technique for automatically training a set of character templates using unsegmented training samples uses as input a two-dimensional (2D) image of characters, called glyphs, as the source of training samples, a transcription associated with the 2D image as a source of labels for the glyph samples, and an explicit, formal 2D image source model that models as a grammar the structural and functional features of a set of 2D images that may be used as the source of training data. The input transcription may be a literal transcription associated with the 2D input image, or it may be nonliteral, for example containing logical structure tags for document formatting, such as found in markup languages. The technique uses spatial positioning information about the 2D image modeled by the 2D image source model and uses labels in the transcription to determine labeled glyph positions in the 2D image that identify locations of glyph samples. The character templates are produced using the input 2D image and the labeled glyph positions without assigning pixels to glyph samples prior to training. In one implementation, the 2D image source model is a regular grammar having the form of a finite state transition network, and the transcription is also represented as a finite state network. The two networks are merged to produce a transcription-image network, which is used to decode the input 2D image to produce labeled glyph positions that identify training data samples in the 2D image. In one implementation of the template construction process, a pixel scoring technique is used to produce character templates contemporaneously from blocks of training data samples aligned at glyph positions.

Abstract translation: 用于使用未分段训练样本自动训练一组角色模板的技术将作为训练样本的来源的称为字形的二维（2D）图像的字符（2D）用作输入，与2D图像相关联的转录作为标签的来源 对于字形样本，以及一个明确的，正式的2D图像源模型，其将模型化为可以用作训练数据源的一组2D图像的结构和功能特征作为语法。 输入转录可以是与2D输入图像相关联的文字转录，或者它可以是非标准的，例如包含用于文档格式化的逻辑结构标签，例如以标记语言找到的。 该技术使用关于由2D图像源模型建模的2D图像的空间定位信息，并使用转录中的标签来确定2D图像中识别字形样本位置的标记字形位置。 使用输入的2D图像和标记的字形位置产生字符模板，而不在训练之前将像素分配给字形样本。 在一个实现中，2D图像源模型是具有有限状态转换网络形式的规则语法，并且转录也被表示为有限状态网络。 两个网络被合并以产生转录图像网络，其用于解码输入的2D图像以产生识别2D图像中的训练数据样本的标记的字形位置。 在模板构建过程的一个实现中，使用像素评分技术从与字形位置对齐的训练数据样本的块同时产生字符模板。

公开(公告)号：US08842752B2

公开(公告)日：2014-09-23

申请号：US13052667

申请日：2011-03-21

Applicant: Amer A. Hassan ,  Christian Huitema ,  Wayne Stark ,  Yunnan Wu ,  Philip Andrew Chou

Inventor： Amer A. Hassan ,  Christian Huitema ,  Wayne Stark ,  Yunnan Wu ,  Philip Andrew Chou

IPC: H04L27/28 ,  H04L5/00 ,  H04L1/00

CPC classification number: H04W72/08 ,  H04L1/0045 ,  H04L1/0071 ,  H04L5/0007 ,  H04L5/0041 ,  H04L5/0046 ,  H04L5/0058 ,  H04L5/006 ,  H04L2001/0093

Abstract: A multiuser scheme allowing for a number of users, sets of user, or carriers to share one or more channels is provided. In the invention, the available channel bandwidth is subdivided into a number of equal-bandwidth subchannels according to standard OFDM practice. A transmitter transmits data on a set of OFDM subchannels that need not be contiguous in the spectrum or belong to the same OFDM channel. A receiver receives and decodes the data and detects errors on subchannels. The receiver then broadcasts the identity of those subchannels on which the error rate exceeds a specific threshold, and the transmitter may select different subchannels for transmission based on this information.

Abstract translation: 提供允许多个用户，一组用户或运营商共享一个或多个信道的多用户方案。 在本发明中，可用的信道带宽根据标准OFDM实践被细分为多个等带宽子信道。 发射机在不需要在频谱中连续或属于相同OFDM信道的一组OFDM子信道上发送数据。 接收器接收并解码数据并检测子信道上的错误。 然后，接收机广播差错率超过特定阈值的子信道的身份，并且发射机可以基于该信息来选择用于发送的不同子信道。

公开(公告)号：US20110173485A1

公开(公告)日：2011-07-14

申请号：US13052667

申请日：2011-03-21

Applicant: Amer A. Hassan ,  Christian Huitema ,  Wayne Stark ,  Yunnan Wu ,  Philip Andrew Chou

Inventor： Amer A. Hassan ,  Christian Huitema ,  Wayne Stark ,  Yunnan Wu ,  Philip Andrew Chou

IPC: G06F11/07

CPC classification number: H04W72/08 ,  H04L1/0045 ,  H04L1/0071 ,  H04L5/0007 ,  H04L5/0041 ,  H04L5/0046 ,  H04L5/0058 ,  H04L5/006 ,  H04L2001/0093

Abstract: A multiuser scheme allowing for a number of users, sets of user, or carriers to share one or more channels is provided. In the invention, the available channel bandwidth is subdivided into a number of equal-bandwidth subchannels according to standard OFDM practice. A transmitter transmits data on a set of OFDM subchannels that need not be contiguous in the spectrum or belong to the same OFDM channel. A receiver receives and decodes the data and detects errors on subchannels. The receiver then broadcasts the identity of those subchannels on which the error rate exceeds a specific threshold, and the transmitter may select different subchannels for transmission based on this information.

Abstract translation: 提供允许多个用户，一组用户或运营商共享一个或多个信道的多用户方案。 在本发明中，可用信道带宽根据标准OFDM实践被细分为多个等带宽子信道。 发射机在不需要在频谱中连续或属于相同OFDM信道的一组OFDM子信道上发送数据。 接收器接收并解码数据并检测子信道上的错误。 然后，接收机广播差错率超过特定阈值的子信道的身份，并且发射机可以基于该信息来选择用于发送的不同子信道。

公开(公告)号：US20070283142A1

公开(公告)日：2007-12-06

申请号：US11447470

申请日：2006-06-05

Applicant: David Milstein ,  Philip Andrew Chou ,  Scott C. Forbes ,  Timothy M. Moore

Inventor： David Milstein ,  Philip Andrew Chou ,  Scott C. Forbes ,  Timothy M. Moore

IPC: H04L9/00

CPC classification number: H04L63/08 ,  H04L65/1069

Abstract: Generally described, multimode authentication over a VoIP communication channel is provided. A calling client and a called client may be authenticated for a communication channel establishment. When a calling client requests a call connection with a called client, the calling client is authenticated for the communication channel, based on exchanged contextual information between the calling client and the called client. Likewise, the called client is authenticated for the communication channel by the calling client. Upon authentication, a communication channel is established, over which the calling client and the called client are allowed to exchange more contextual and voice/multimedia information. During a conversation, when a secured service is desired by any of the clients, a series of authentication processes can be performed to grant access to the secured service over the communication channel without loss of the communication channel connection.

Abstract translation: 通常描述，提供了通过VoIP通信信道的多模式认证。 呼叫客户端和被叫客户端可以被认证用于通信信道建立。 当主叫客户端请求与被叫客户端的呼叫连接时，根据主叫客户端和被叫客户端之间交换的上下文信息，对通信信道对呼叫客户端进行身份验证。 同样地，被叫客户端被呼叫客户端认证为通信信道。 在认证时，建立通信信道，通过该通信信道，主叫客户端和被叫客户端被允许交换更多的上下文和语音/多媒体信息。 在对话期间，当任何客户端希望获得安全服务时，可以执行一系列认证过程，以通过通信信道授予对安全服务的访问，而不会丢失通信信道连接。

公开(公告)号：US08842660B2

公开(公告)日：2014-09-23

申请号：US11394578

申请日：2006-03-31

Applicant: David Milstein ,  David A Howell ,  Linda Criddle ,  Michael D Malueg ,  Philip Andrew Chou

Inventor： David Milstein ,  David A Howell ,  Linda Criddle ,  Michael D Malueg ,  Philip Andrew Chou

IPC: H04L12/66 ,  H04M1/56 ,  H04M15/06 ,  H04M1/57 ,  H04M3/42

CPC classification number: H04M1/571 ,  H04L12/66 ,  H04M1/575 ,  H04M3/42025

Abstract: A method and system for communicating a variable set of contextual information relating to a conversation over a communication channel is provided. When the contextual information is exchanged, any authorized sending party of the contextual information can change the scope, content, or amount of the contextual information that is transmitted to a next receiving party in a determined communication channel path. Before transmitting the contextual information, a desirable scope of the contextual information may be determined based on the next receiving party, in conjunction with the sending party's rules. The contextual information may be updated by adding new contextual information and/or deleting part of the contextual information which is outside of the scope. No contextual information may be transmitted if the next destination desires no contextual information or does not have capabilities to receive any contextual information.

Abstract translation: 提供了一种用于在通信信道上传送与会话相关的可变的上下文信息集合的方法和系统。 当上下文信息被交换时，上下文信息的任何授权的发送方可以改变在确定的通信信道路径中发送给下一个接收方的上下文信息的范围，内容或量。 在发送上下文信息之前，可以结合发送方的规则，基于下一个接收方来确定上下文信息的期望范围。 可以通过添加新的上下文信息和/或删除在范围之外的上下文信息的一部分来更新上下文信息。 如果下一个目的地不需要上下文信息或者不具有接收任何上下文信息的能力，则不会发送上下文信息。

公开(公告)号：US5689585A

公开(公告)日：1997-11-18

申请号：US431004

申请日：1995-04-28

Applicant: Dan S. Bloomberg ,  Leslie T. Niles ,  Gary E. Kopec ,  Philip Andrew Chou

Inventor： Dan S. Bloomberg ,  Leslie T. Niles ,  Gary E. Kopec ,  Philip Andrew Chou

IPC: G06K9/20 ,  G06K9/72

CPC classification number: G06K9/00469 ,  G06K9/72 ,  G06K2209/01

Abstract: A method for establishing a relationship between a text image and a transcription associated with the text image uses conventional image processing techniques to identify one or more geometric attributes, or image parameters, of each of a sequence of regions of the text image. The transcription labels in the transcription are analyzed to determine a comparable set of parameters in transcription label sequence. A matching operation then matches the respective parameters of the two sequences to identify image regions that match with transcription regions. The result is an output data structure that minimally identifies image locations of interest to a subsequent operation that processes the text image. The output data structure may also pair each of the image locations of interest to a transcription location, in effect producing a set of labeled image locations. In one embodiment, the sequence of locations of words and their observed lengths in the text image are determined. The transcription is analyzed to identify words, and transcription word lengths are computed using an estimated image character width of glyphs in the text image. The sequence of observed image word lengths is then matched to the sequence of computed transcription word lengths using a dynamic programming algorithm that finds a best path through a two-dimensional lattice of nodes and transitions between nodes, where the transitions represent pairs of sequences of zero or more word lengths. An output data structure contains entries, each of which pairs a transcription word with a matching image word location.

Abstract translation: 用于建立文本图像与与文本图像相关联的转录之间的关系的方法使用常规图像处理技术来识别文本图像的区域序列中的每一个的一个或多个几何属性或图像参数。 分析转录中的转录标记以确定转录标记序列中可比较的一组参数。 匹配操作然后匹配两个序列的相应参数以识别与转录区域匹配的图像区域。 结果是输出数据结构，其最小程度地识别处理文本图像的后续操作感兴趣的图像位置。 输出数据结构还可以将感兴趣的每个图像位置配对到转录位置，实际上产生一组标记的图像位置。 在一个实施例中，确定单词的位置序列及其在文本图像中的观察长度。 分析转录以识别词，并且使用文本图像中的字形的估计图像字符宽度来计算转录词长度。 然后使用动态规划算法将观察到的图像字长度的序列与计算出的转录词长度的序列匹配，该动态规划算法通过节点的二维网格和节点之间的转换找到最佳路径，其中，转换代表零序列对 或更多字长。 输出数据结构包含条目，每个条目将转录词与匹配的图像字位置配对。