公开(公告)号：US20090135735A1

公开(公告)日：2009-05-28

申请号：US12082021

申请日：2008-04-08

申请人： Peng Zhang ,  Rafid A. Sukkar ,  Jeffrey A. Hawbaker

发明人： Peng Zhang ,  Rafid A. Sukkar ,  Jeffrey A. Hawbaker

IPC分类号： H04L12/56 ,  G06F11/00

CPC分类号： H04L65/608

摘要： Media processing of real-time protocol (RTP) packets used in time sensitive applications makes efficient use of network resources, e.g., by dropping or resizing the packets, but hinders measuring and reporting end-to-end reception quality. Because media processing causes a difference between what is sent and received, end-to-end reception quality cannot be measured validly without accounting for this difference. Accordingly, a method and corresponding apparatus are provided to track changes to RTP packets of an RTP session caused by media processing, modify RTP packet information of the RTP packets based on the tracked changes, correct RTP control protocol (RTCP) packets corresponding to the RTP session based on the tracked changes, the corrected RTCP packets being a measure of the end-to-end reception quality of the RTP session, and report the end-to-end reception quality of the RTP session by forwarding the corrected RTCP packets. Thus, end-to-end reception quality can be validly measured and reported.

摘要翻译： 在时间敏感应用中使用的实时协议（RTP）分组的媒体处理使得有效利用网络资源，例如通过丢弃或调整分组大小，但是阻碍测量和报告端到端的接收质量。 由于媒体处理造成发送和接收的差异，端到端接收质量无法有效测量，而不考虑这种差异。 因此，提供了一种方法和相应的装置来跟踪由媒体处理引起的RTP会话的RTP分组的变化，基于跟踪的改变来修改RTP分组的RTP分组信息，对应于RTP的正确的RTP控制协议（RTCP）分组 会话基于跟踪的变化，校正的RTCP分组是RTP会话的端对端接收质量的量度，并且通过转发校正的RTCP分组来报告RTP会话的端到端接收质量。 因此，可以有效地测量和报告端到端的接收质量。

公开(公告)号：US20090135724A1

公开(公告)日：2009-05-28

申请号：US11986983

申请日：2007-11-27

申请人： Peng Zhang ,  Jeffrey A. Hawbaker ,  Rafid A. Sukkar

发明人： Peng Zhang ,  Jeffrey A. Hawbaker ,  Rafid A. Sukkar

IPC分类号： H04L12/26

CPC分类号： H04L41/5032 ,  H04L41/5025 ,  H04L65/608 ,  H04L65/80

摘要： Media processing of real-time protocol (RTP) packets used in Voice over Internet Protocol (VoIP) and other time sensitive applications makes efficient use of network resources, e.g., by dropping or changing the size of certain packets, but hinders measuring and reporting end-to-end reception quality. Because media processing changes RTP packets between a sender and receiver, causing a difference between what is sent and received, end-to-end reception quality cannot be measured validly without accounting for these changes. Accordingly, a method and corresponding apparatus are provided to track changes to RTP packets of an RTP session caused by media processing of the RTP packets, modify RTP packet information of the RTP packets based on the tracked changes, correct RTP control protocol (RTCP) packets corresponding to the RTP session based on the tracked changes, the corrected RTCP packets being a measure of the end-to-end reception quality of the RTP session, and report the end-to-end reception quality of the RTP session by forwarding the corrected RTCP packets.

摘要翻译： 媒体处理通过互联网协议语音（VoIP）和其他时间敏感应用程序使用的实时协议（RTP）数据包可以有效利用网络资源，例如通过删除或更改某些数据包的大小，但阻碍测量和报告结束 端到端接收质量。 由于媒体处理改变发送方和接收方之间的RTP数据包，导致发送和接收之间的差异，端到端接收质量无法有效测量，而不考虑这些变化。 因此，提供了一种方法和相应的装置，以跟踪由RTP分组的媒体处理引起的RTP会话的RTP分组的改变，基于跟踪的改变修改RTP分组的RTP分组信息，修改RTP控制协议（RTCP）分组 对应于基于跟踪变化的RTP会话，校正的RTCP分组是RTP会话的端对端接收质量的量度，并且通过转发经修正的RTP会话来报告RTP会话的端到端接收质量 RTCP数据包。

公开(公告)号：US08874437B2

公开(公告)日：2014-10-28

申请号：US11165599

申请日：2005-06-22

申请人： Rafid A. Sukkar ,  Richard C. Younce ,  Peng Zhang

发明人： Rafid A. Sukkar ,  Richard C. Younce ,  Peng Zhang

IPC分类号： G10L21/00 ,  G10L19/083

CPC分类号： G10L21/0205 ,  G10L19/083 ,  G10L21/0364

摘要： Adaptive Gain Control (AGC) is performed directly in a coded domain. A Coded Domain Adaptive Gain Control (CD-AGC) system modifies at least one parameter of a first encoded signal, resulting in corresponding modified parameter(s). The CD-VQE system replaces the parameter(s) of the first encoded signal with the modified parameter(s), resulting in a second encoded signal. In a decoded state, the second encoded signal approximates a target signal that is a function of two signals, including the first encoded signal and a third encoded signal, in at least a partially decoded states. Thus, the first encoded signal does not have to go through intermediate decode/re-encode processes, which can degrade overall speech quality. Computational resources required for a complete re-encoding are not needed. Overall delay of the system is minimized. The CD-AGC system can be used in any network in which signals are communicated in a coded domain, such as a Third Generation (3G) wireless network.

摘要翻译： 自适应增益控制（AGC）直接在编码域中执行。 编码域自适应增益控制（CD-AGC）系统修改第一编码信号的至少一个参数，导致相应的修改参数。 CD-VQE系统用修改的参数替换第一编码信号的参数，从而产生第二编码信号。 在解码状态下，第二编码信号在至少部分解码状态下近似作为包括第一编码信号和第三编码信号的两个信号的函数的目标信号。 因此，第一编码信号不必经历中间解码/重编码处理，这可能降低总体语音质量。 不需要完全重新编码所需的计算资源。 系统的整体延迟最小化。 CD-AGC系统可以用于信号在诸如第三代（3G）无线网络的编码域中传送的任何网络中。

公开(公告)号：US20090257455A1

公开(公告)日：2009-10-15

申请号：US12082890

申请日：2008-04-15

申请人： Rafid A. Sukkar ,  Peng Zhang

发明人： Rafid A. Sukkar ,  Peng Zhang

IPC分类号： H04J3/06

CPC分类号： H04J3/0664 ,  H04L47/10 ,  H04L47/28 ,  H04L65/80 ,  H04L69/28

摘要： In some communications systems, unsynchronized near-end and far-end packets of communications signals can reduce or impair performance of processing of packets, such as to the case of Coded Domain Media Quality Enhancement. Therefore, a system may synchronize the incoming signals to enhance quality. A relative delay determination module according to an example embodiment of this invention determines a synchronization and relative delay between packets belonging to different packet streams arriving at a network node in a packet-based network by computing a time synchronization parameter based on a time reference of timestamps of the signals and reports the relative delay to a module making use of the relative delay such as a voice quality enhancement or an echo control module. By synchronizing the packets at the location within the network, source clocks at end or edge nodes of the network can operate with reduced synchronization, simplifying network operations and management thereof.

摘要翻译： 在一些通信系统中，通信信号的不同步的近端和远端分组可以减少或削弱分组处理的性能，例如编码域媒体质量增强的情况。 因此，系统可以使输入信号同步以提高质量。 根据本发明的示例实施例的相对延迟确定模块通过基于时间戳的时间参考计算时间同步参数来确定属于基于分组的网络中的网络节点处的不同分组流的分组之间的同步和相对延迟 的信号，并将相对延迟报告给使用诸如语音质量增强或回波控制模块之类的相对延迟的模块。 通过在网络内的位置同步数据包，网络的端点或边缘节点的源时钟可以减少同步操作，简化网络操作及其管理。

公开(公告)号：US20070263851A1

公开(公告)日：2007-11-15

申请号：US11449478

申请日：2006-06-07

申请人： Rafid A. Sukkar ,  Peng Zhang

发明人： Rafid A. Sukkar ,  Peng Zhang

IPC分类号： H04M9/08

CPC分类号： H04B3/23

摘要： A method, apparatus, system, and program, for evaluating a call communicated between communicating devices through at least one communication path. The method comprises segmenting, into first segments, at least one first communication signal traveling from a first one of the communicating devices to a second one of the communicating devices through the at least one communication path, and segmenting, into second segments, at least one second communication signal traveling from the second one of the communicating devices to the first one of the communicating devices through the at least one communication path. The method also comprises determining predetermined call characteristics based on the first and second segments, and identifying whether an echo is present in the call based on a result of the determining.

摘要翻译： 一种用于评估通过至少一个通信路径在通信设备之间传送的呼叫的方法，装置，系统和程序。 该方法包括：通过至少一个通信路径将至少一个从通信设备中的第一通信设备传送到通信设备的第二通信信号的至少一个第一通信信号分段成第二段，至少一个 第二通信信号通过至少一个通信路径从通信设备中的第二通信设备传送到通信设备的第一通信信号。 该方法还包括基于第一和第二段确定预定的呼叫特性，并且基于确定的结果来识别呼叫中是否存在回声。

公开(公告)号：US5440662A

公开(公告)日：1995-08-08

申请号：US989299

申请日：1992-12-11

申请人： Rafid A. Sukkar

发明人： Rafid A. Sukkar

IPC分类号： G10L15/00 ,  G10L15/14 ,  G10L9/18

CPC分类号： G10L15/142 ,  G10L2015/088

摘要： A two-pass classification system and method that post-processes HMM scores with additional confidence scores to derive a value that may be applied to a threshold on which a keyword verses non-keyword determination may be based. The first stage comprises Generalized Probabilistic Descent (GPD) analysis which uses feature vectors of the spoken words and the HMM segmentation information (developed by the HMM detector during processing) as inputs to develop a first set of confidence scores through a linear combination (a weighted sum) of the feature vectors of the speech. The second stage comprises a linear discrimination method that combines the HMM scores and the confidence scores from the GPD stage with a weighted sum to derive a second confidence score. The output of the second stage may then be compared to a predetermined threshold to determine whether the spoken word or words include a keyword.

摘要翻译： 一种二次分类系统和方法，其用附加的置信度得分后处理HMM得分，以导出可应用于关键词对应于非关键字确定的阈值的值。 第一阶段包括广义概率下降（GPD）分析，其使用口语单词的特征向量和HMM分割信息（由处理期间由HMM检测器开发）作为输入，以通过线性组合（加权 总和）的语音特征向量。 第二阶段包括线性判别方法，其将HMM评分与来自GPD阶段的置信度得分与加权和相结合以得到第二置信度分数。 然后可以将第二级的输出与预定阈值进行比较，以确定口头单词或单词是否包括关键词。

公开(公告)号：US08032365B2

公开(公告)日：2011-10-04

申请号：US11975419

申请日：2007-10-19

申请人： Rafid A. Sukkar

发明人： Rafid A. Sukkar

IPC分类号： H04M9/08 ,  G06F15/00 ,  G10L21/02 ,  A61F11/06 ,  G10K11/16 ,  G10L21/00

CPC分类号： H04M9/082

摘要： A method and corresponding apparatus for coded-domain acoustic echo control is presented. An echo control problem is considered as that of perceptually matching an echo signal to a reference signal. A perceptual similarity function that is based on the coded spectral parameters produced by the speech codec is defined. Since codecs introduce a significant degree of non-linearity into the echo signal, the similarity function is designed to be robust against such effects. The similarity function is incorporated into a coded-domain echo control system that also includes spectrally-matched noise injection for replacing echo frames with comfort noise. Using actual echoes recorded over a commercial mobile network, it is shown herein that the similarity function is robust against both codec non-linearities and additive noise. Experimental results further show that the echo-control is effective at suppressing echoes compared to a Normalized Least Mean Squared (NLMS)-based echo cancellation system.

摘要翻译： 提出了一种用于编码域声学回声控制的方法和相应装置。 回声控制问题被认为是将回波信号与参考信号感知地匹配的问题。 定义了基于由语音编解码器产生的编码频谱参数的知觉相似度函数。 由于编解码器将重要程度的非线性引入到回波信号中，所以相似度函数被设计为对这种效应是鲁棒的。 相似度功能被并入编码域回波控制系统中，该系统还包括用于用舒适噪声替换回波帧的频谱匹配噪声注入。 使用在商业移动网络上记录的实际回波，这里示出了相似度函数对编解码器非线性和加性噪声都是鲁棒的。 实验结果进一步表明，与基于归一化最小均方（NLMS）的回波消除系统相比，回波控制在抑制回波方面是有效的。

公开(公告)号：US5613037A

公开(公告)日：1997-03-18

申请号：US171071

申请日：1993-12-21

申请人： Rafid A. Sukkar

发明人： Rafid A. Sukkar

IPC分类号： G10L15/14 ,  G10L5/06

CPC分类号： G10L15/142 ,  G10L15/144

摘要： A high reliability digit string recognizer/rejection system that processes spoken words through an HMM recognizer to determine a string of candidate digits, a filler model for each digit in the digit string, and other information. Next, a weighted sum is generated for each digit in the string and for a filler model for each digit in the string. A confidence score is generated for each digit by subtracting the filler weighted sum from the digit weighted sum. The confidence score for each digit is then compared to a threshold and, if the confidence score for any of the digits is less than the threshold, the entire digit string is rejected. If the confidence scores for all of the digits in the digit string are equal to or greater than the threshold, then the candidate digit string is accepted as a digit string.

摘要翻译： 一种高可靠性数字串识别/排除系统，其通过HMM识别器处理口语，以确定候选数字串，数字串中每个数字的填充模型以及其他信息。 接下来，为字符串中的每个数字和字符串中每个数字的填充模型生成加权和。 通过从数字加权和中减去填充物加权和，为每个数字产生置信度分数。 然后将每个数字的置信分数与阈值进行比较，如果任何数字的置信度分数小于阈值，则整个数字串被拒绝。 如果数字串中所有数字的置信分数等于或大于阈值，则候选数字串被接受为数字串。

公开(公告)号：US20130155924A1

公开(公告)日：2013-06-20

申请号：US13327228

申请日：2011-12-15

申请人： Rafid A. Sukkar

发明人： Rafid A. Sukkar

IPC分类号： H04M9/08 ,  H04W52/02

CPC分类号： H04M9/082

摘要： A system, apparatus, method, and computer-readable medium for coded-domain echo cancellation. The method includes receiving a signal including at least one packet, and replacing the at least one packet with a replacement packet. In one example, the replacement packet is a comfort noise packet (such as a SID_UPDATE packet) or a NO_DATA packet. In an example embodiment, the at least one packet included in the signal includes one or more comfort noise packets, and, prior to the replacing, the one or more comfort noise packet(s) are stored in a buffer. In another example, prior to the replacing, the at least one packet is compared to a reference packet to determine whether the at least one packet is an echo packet. The packet, in one example, is encoded based on an adaptive multi-rate (AMR) (e.g., AMR-NB or AMR-WB) codec.

摘要翻译： 用于编码域回声消除的系统，装置，方法和计算机可读介质。 该方法包括接收包括至少一个分组的信号，并用替换分组替换该至少一个分组。 在一个示例中，替换分组是舒适噪声分组（诸如SID_UPDATE分组）或NO_DATA分组。 在示例实施例中，包括在信号中的至少一个分组包括一个或多个舒适噪声分组，并且在更换之前，将一个或多个舒适噪声分组存储在缓冲器中。 在另一示例中，在替换之前，将至少一个分组与参考分组进行比较，以确定该至少一个分组是否是回波分组。 在一个示例中，分组基于自适应多速率（AMR）（例如，AMR-NB或AMR-WB）编解码器进行编码。

公开(公告)号：US20120063591A1

公开(公告)日：2012-03-15

申请号：US13229357

申请日：2011-09-09

申请人： Rafid A. Sukkar

发明人： Rafid A. Sukkar

IPC分类号： H04M9/08

CPC分类号： H04M9/082

摘要： A method and corresponding apparatus for coded-domain acoustic echo control is presented. An echo control problem is considered as that of perceptually matching an echo signal to a reference signal. A perceptual similarity function that is based on the coded spectral parameters produced by the speech codec is defined. Since codecs introduce a significant degree of non-linearity into the echo signal, the similarity function is designed to be robust against such effects. The similarity function is incorporated into a coded-domain echo control system that also includes spectrally-matched noise injection for replacing echo frames with comfort noise. Using actual echoes recorded over a commercial mobile network, it is shown herein that the similarity function is robust against both codec non-linearities and additive noise. Experimental results further show that the echo-control is effective at suppressing echoes compared to a Normalized Least Mean Squared (NLMS)-based echo cancellation system.

摘要翻译： 提出了一种用于编码域声学回声控制的方法和相应装置。 回声控制问题被认为是将回波信号与参考信号感知地匹配的问题。 定义了基于由语音编解码器产生的编码频谱参数的知觉相似度函数。 由于编解码器将重要程度的非线性引入到回波信号中，所以相似度函数被设计为对这种效应是鲁棒的。 相似度功能被并入编码域回波控制系统中，该系统还包括用于用舒适噪声替换回波帧的频谱匹配噪声注入。 使用在商业移动网络上记录的实际回波，这里示出了相似度函数对编解码器非线性和加性噪声都是鲁棒的。 实验结果进一步表明，与基于归一化最小均方（NLMS）的回波消除系统相比，回波控制在抑制回波方面是有效的。