公开(公告)号：US08983089B1

公开(公告)日：2015-03-17

申请号：US13305189

申请日：2011-11-28

申请人： Wai C. Chu ,  Edward Dietz Crump

发明人： Wai C. Chu ,  Edward Dietz Crump

IPC分类号： H04R3/00 ,  H04R29/00

CPC分类号： G10L15/28 ,  H04R1/08 ,  H04R3/005 ,  H04R27/00 ,  H04R2227/003

摘要： An augmented reality environment allows interaction between virtual and real objects. Multiple microphone arrays of different physical sizes are used to acquire signals for spatial tracking of one or more sound sources within the environment. A first array with a larger size may be used to track an object beyond a threshold distance, while a second array having a size smaller than the first may be used to track the object up to the threshold distance. By selecting different sized arrays, accuracy of the spatial location is improved.

摘要翻译： 增强的现实环境允许虚拟和实际对象之间的交互。 使用不同物理尺寸的多个麦克风阵列来获取用于环境内的一个或多个声源的空间跟踪的信号。 可以使用具有较大尺寸的第一阵列来跟踪超过阈值距离的对象，而具有小于第一尺寸的尺寸的第二阵列可以用于跟踪该物体直到阈值距离。 通过选择不同大小的阵列，提高了空间位置的准确性。

公开(公告)号：US09373338B1

公开(公告)日：2016-06-21

申请号：US13532649

申请日：2012-06-25

申请人： Ramya Gopalan ,  Kavitha Velusamy ,  Wai C. Chu ,  Amit S. Chhetri

发明人： Ramya Gopalan ,  Kavitha Velusamy ,  Wai C. Chu ,  Amit S. Chhetri

IPC分类号： G10L21/02

CPC分类号： G10L21/02 ,  G10L15/22 ,  G10L15/26 ,  H04M9/082

摘要： An automatic speech recognition engine receives an acoustic-echo processed signal from an acoustic-echo processing (AEP) module, where said echo processed signal contains mainly the speech from the near-end talker. The automatic speech recognition engine analyzes the content of the acoustic-echo processed signal to determine whether words or keywords are present. Based upon the results of this analysis, the automatic speech recognition engine produces a value reflecting the likelihood that some words or keywords are detected. Said value is provided to the AEP module. Based upon the value, the AEP module determines if there is double talk and processes the incoming signals accordingly to enhance its performance.

摘要翻译： 自动语音识别引擎从声学回波处理（AEP）模块接收声学回波处理的信号，其中所述回波处理的信号主要包含来自近端讲话者的语音。 自动语音识别引擎分析声回波处理信号的内容，以确定是否存在词或关键词。 基于该分析的结果，自动语音识别引擎产生反映检测到某些单词或关键词的可能性的值。 所述值被提供给AEP模块。 基于该值，AEP模块确定是否存在双重通话，并相应地处理输入信号以增强其性能。

公开(公告)号：US09351089B1

公开(公告)日：2016-05-24

申请号：US13420451

申请日：2012-03-14

申请人： Wai C. Chu

发明人： Wai C. Chu

IPC分类号： H04R29/00 ,  H02B1/00

CPC分类号： H04R29/004 ,  G01H3/14 ,  G06F3/011 ,  G06F3/017 ,  G06F2200/1636 ,  G10H2210/071 ,  H04R29/00

摘要： Techniques are described for recognizing an audio double tap or other tapped audio sequences generated by a user. Amplitudes of an audio signal are processed to generate an energy function or curve. The energy curve is analyzed to detect audio pulses. Detected pulses are validated and double tap events are detected based on features such as duration, power, and/or symmetry, plus additional rules related to the structure of the audio event.

摘要翻译： 描述了用于识别由用户生成的音频双抽头或其他抽头音频序列的技术。 处理音频信号的幅度以产生能量函数或曲线。 分析能量曲线以检测音频脉冲。 检测到的脉冲被验证，并且基于诸如持续时间，功率和/或对称性的特征以及与音频事件的结构相关的附加规则来检测双击事件。

公开(公告)号：US07512534B2

公开(公告)日：2009-03-31

申请号：US11595415

申请日：2006-11-09

申请人： Wai C. Chu

发明人： Wai C. Chu

IPC分类号： G10L19/14 ,  G10L19/00

CPC分类号： G10L19/032 ,  G10L19/022 ,  G10L19/07

摘要： Primary and alternate optimization procedures are used to improve the ITU-T G.723.1 speech coding standard (the “Standard”) by replacing the Hamming window of the Standard with an optimized window, with two windows, or with two windows and an additional performance of an autocorrelation method. When two windows replace the Hamming window, at least one of which is an optimized window, generally the first is used to determine optimized unquantized LP coefficients which are used to define an optimized perceptual weighting filter, and the second is used to determine optimized unquantized LP coefficients which are used to determine optimized synthesis coefficients. Optimized windows created using the primary and alternate optimization procedures and used in the Standard yield improvements in the objective and subjective quality of synthesized speech produced by the Standard. The improved Standard, methods, and widow can all be implemented as computer readable software code.

摘要翻译： 主要和替代优化程序用于通过用优化的窗口替换标准的汉明窗口，具有两个窗口或两个窗口和附加的性能来改进ITU-T G.723.1语音编码标准（“标准”） 的自相关方法。 当两个窗口替换汉明窗口时，其中至少一个是优化的窗口，通常第一个窗口用于确定用于定义优化的感知加权滤波器的优化的无量纲LP系数，第二个用于确定优化的无量纲LP 用于确定优化的合成系数的系数。 使用主要和替代优化程序创建的优化窗口，并在标准中用于标准产生的合成语音的客观和主观质量的改进。 改进的标准，方法和寡妇都可以实现为计算机可读软件代码。

公开(公告)号：US09560446B1

公开(公告)日：2017-01-31

申请号：US13535135

申请日：2012-06-27

申请人： Samuel Henry Chang ,  Wai C. Chu

发明人： Samuel Henry Chang ,  Wai C. Chu

IPC分类号： G06F17/00 ,  H04R3/00

CPC分类号： H04R3/005 ,  H04R1/406 ,  H04R2201/403 ,  H04R2430/20

摘要： A sound source locator efficiently employs a distributed physical or logical microphone array to determine a location of a source of a sound. In some instances, the sound source locator is deployed in an augmented reality environment. The sound source locator detects sound at a plurality of microphones, generates a signal corresponding to the sound, and causes attributes of signal as generated at the plurality of microphones to be stored in association with the corresponding microphone. The sound source locator uses these stored attributes to identify multiple groups of the plurality of microphones from which delays between the times the signal is generated can be used to compute the location of the source of the sound.

摘要翻译： 声源定位器有效地使用分布式物理或逻辑麦克风阵列来确定声源的位置。 在某些情况下，声源定位器部署在增强现实环境中。 声源定位器检测多个麦克风处的声音，产生对应于声音的信号，并且使与多个麦克风相关联地存储在多个麦克风处产生的信号的属性被存储。 声源定位器使用这些存储的属性来识别多个麦克风的多个组，从该信号生成的时间之间的延迟可用于计算声源的位置。

公开(公告)号：US08582906B2

公开(公告)日：2013-11-12

申请号：US12716839

申请日：2010-03-03

申请人： Wai C. Chu ,  David J. Pattridge

发明人： Wai C. Chu ,  David J. Pattridge

IPC分类号： G06K9/36 ,  G06K9/00

CPC分类号： G06K9/36

摘要： Compression and decompression of image data, including a first image of an object. The first image may be divided into portions. For each portion, it may be determined whether the portion includes a part of the object. The image data may be compressed based on said determining. If a threshold ratio of portions that do not include a part of the object is reached, portions including a part of the object may be compressed according to a first compression method and portions not including a part of the object may not be compressed, where background information is stored for the portions not including a part of the object. If the threshold ratio of portions that do not include a part of the object is not reached, each portion of the object may be compressed according to the first compression method. The compressed data may be decompressed in a reverse fashion.

摘要翻译： 图像数据的压缩和解压缩，包括对象的第一个图像。 第一图像可以被分成几部分。 对于每个部分，可以确定该部分是否包括对象的一部分。 可以基于所述确定来压缩图像数据。 如果到达不包括对象的一部分的部分的阈值比率，则可以根据第一压缩方法来压缩包括对象的一部分的部分，并且不包括对象的一部分的部分可以不被压缩，其中背景 对于不包括对象的一部分的部分存储信息。 如果没有到达不包括对象的一部分的部分的阈值比率，则可以根据第一压缩方法来压缩对象的每个部分。 压缩数据可以以相反的方式解压缩。

公开(公告)号：US09767828B1

公开(公告)日：2017-09-19

申请号：US13535232

申请日：2012-06-27

申请人： Kavitha Velusamy ,  Wai C. Chu ,  Ramya Gopalan ,  Amit S. Chhetri

发明人： Kavitha Velusamy ,  Wai C. Chu ,  Ramya Gopalan ,  Amit S. Chhetri

IPC分类号： G06K9/00 ,  G10L25/78 ,  H04N21/442 ,  H04B3/23

CPC分类号： G10L25/78 ,  G06K9/00268 ,  G06K9/00335 ,  G06K9/00362 ,  G10L17/00 ,  G10L21/0208 ,  G10L2021/02082 ,  H04B3/23 ,  H04B3/231 ,  H04N21/44218

摘要： Techniques for enhancing an acoustic echo canceller based on visual cues are described herein. The techniques include changing adaptation of a filter of the acoustic echo canceller, calibrating the filter, or reducing background noise from an audio signal processed by the acoustic echo canceller. The changing, calibrating, and reducing are responsive to visual cues that describe acoustic characteristics of a location of a device that includes the acoustic echo canceller. Such visual cues may indicate that no human being is present at the location, that some subject(s) are engaged in speaking or sound generating activities, or that motion associated with an echo path change has occurred at the location.

公开(公告)号：US09081083B1

公开(公告)日：2015-07-14

申请号：US13169826

申请日：2011-06-27

申请人： Wai C. Chu

发明人： Wai C. Chu

IPC分类号： G01S5/20 ,  G01S5/22

CPC分类号： G01S5/20 ,  G01S3/801 ,  G01S3/808 ,  G01S5/18 ,  G01S5/22

摘要： Accurate and computationally efficient estimation of time delay of arrival data for localization of a sound source is described herein. A number of independent time delays are retained and validated through comparison with a set of dependent time delays. The method is robust against detrimental effects in the environment such as noise and reverberation. The resulting delays may then be used in sound source localization or other signal processing applications.

摘要翻译： 本文描述了用于定位声源的到达数据的时间延迟的精确和计算有效的估计。 通过与一组依赖时间延迟进行比较，保留并验证了许多独立的时间延迟。 该方法对于诸如噪声和混响等环境的有害影响是有效的。 所产生的延迟可以用于声源定位或其他信号处理应用中。

公开(公告)号：US08855295B1

公开(公告)日：2014-10-07

申请号：US13532617

申请日：2012-06-25

申请人： Amit S. Chhetri ,  Kavitha Velusamy ,  Wai C. Chu ,  Ramya Gopalan

发明人： Amit S. Chhetri ,  Kavitha Velusamy ,  Wai C. Chu ,  Ramya Gopalan

IPC分类号： H04M9/08 ,  G10K11/00

CPC分类号： H04M9/082 ,  G10L21/0272

摘要： Techniques for utilizing blind source separation as a front-end to an acoustic echo canceller are described herein. The techniques include removing a first portion of an acoustic echo from an audio signal using blind source separation and a reference signal. The techniques then further remove a second portion of the acoustic echo using an acoustic echo canceller and the reference signal. Further, output of the blind source separation may be used to improve double-talk detection.

摘要翻译： 本文描述了将盲源分离用作声学回声消除器的前端的技术。 这些技术包括使用盲源分离和参考信号从音频信号中去除声学回声的第一部分。 然后，技术使用声学回声消除器和参考信号进一步去除声学回声的第二部分。 此外，盲源分离的输出可以用于改善双方通话检测。

公开(公告)号：US07231344B2

公开(公告)日：2007-06-12

申请号：US10282966

申请日：2002-10-29

申请人： Wai C. Chu

发明人： Wai C. Chu

IPC分类号： G10L19/00 ,  G10L19/14

CPC分类号： G10L19/022 ,  G10L19/04 ,  G10L25/12

摘要： The shape of windows used during linear predictive analysis can be optimized through the use of gradient-descent based window optimization procedures. Window optimization may be achieved fairly precisely through the use of a primary optimization procedure, or less precisely through the use of an alternate optimization procedure. Both optimization procedures use the principle of gradient-descent to find a window sequence that will either minimize the prediction error energy or maximize the segmental prediction gain. However, the primary optimization procedure uses a Levinson-Durbin based algorithm to determine the gradient while the alternate optimization procedure uses an estimate of the gradient based on the basic definition of a derivative. These optimization procedures can be implemented as computer readable software code. Additionally, the optimization procedures may be implemented in a window optimization device which generally includes a window optimization unit and may also include an interface unit.

摘要翻译： 在线性预测分析期间使用的窗口形状可以通过使用基于梯度下降的窗口优化程序进行优化。 窗口优化可以通过使用主要优化过程相当精确地实现，或者通过使用替代优化过程不太精确地实现。 两个优化过程都使用梯度下降原理来找到一个窗口序列，它将最小化预测误差能量或最大化分段预测增益。 然而，主要优化过程使用基于Levinson-Durbin的算法来确定梯度，而替代优化过程使用基于导数的基本定义的梯度估计。 这些优化程序可以实现为计算机可读软件代码。 此外，优化过程可以在通常包括窗口优化单元的窗口优化设备中实现，并且还可以包括接口单元。