-
1.发明公开Method and apparatus for multi-sensory speech enhancement 有权Verfahren und Vorrichtung zur multisensorischenSprachverstärkung
公开(公告)号：EP2431972A1
公开(公告)日：2012-03-21
申请号：EP11008608.9
申请日：2004-10-26
Applicant: Microsoft Corporation
Inventor： Acero, Alejandro , Droppo, James G. , Sinclair, Michael J. , Huang, Xuedong David , Zhang, Zhengyou , Liu, Zicheng , Deng, Li , Zheng, Yanli
IPC: G10L21/02
CPC classification number: G10L21/0208 , G10L2021/02165
Abstract: A method and system use an alternative sensor signal received from a sensor other than an air conduction microphone to estimate a clean speech value. The estimation uses either the alternative sensor signal alone, or in conjunction with the air conduction microphone signal. The clean speech value is estimated without using a model trained from noisy training data collected from an air conduction microphone. Under one embodiment, correction vectors are added to a vector formed from the alternative sensor signal in order to form a filter, which is applied to the air conductive microphone signal to produce the clean speech estimate. In other embodiments, the pitch of a speech signal is determined from the alternative sensor signal and is used to decompose an air conduction microphone signal. The decomposed signal is then used to determine a clean signal estimate.
Abstract translation: 一种方法和系统使用从除了导电麦克风以外的传感器接收的替代传感器信号来估计干净的语音值。 该估计单独使用替代传感器信号，或者与空气传导麦克风信号结合使用。 在不使用从空气传导麦克风收集的噪声训练数据训练的模型的情况下估计干净的语音值。 在一个实施例中，校正矢量被添加到由替代传感器信号形成的矢量中，以便形成滤波器，该滤波器被应用于空气传导麦克风信号以产生干净的语音估计。 在其他实施例中，语音信号的音调由替代传感器信号确定，并用于分解空气传导麦克风信号。 然后使用分解的信号来确定干净的信号估计。
-
公开(公告)号：EP1388794A3
公开(公告)日：2012-02-22
申请号：EP03012896.1
申请日：2003-06-06
Applicant: MICROSOFT CORPORATION
Inventor： Zhang, Zhengyou , Cutler, Ross , He, Li-Wei , Gupta, Anoop , Liu, Zicheng
CPC classification number: G06F17/30843 , G06Q10/1095 , G11B27/105 , G11B27/28 , G11B27/34 , H04N5/77 , H04N9/806
Abstract: A system that captures both whiteboard content and audio signals of a meeting using a digital camera and a microphone. The system can be retrofit to any existing whiteboard. It computes the time stamps of pen strokes on the whiteboard by analyzing the sequence of captured snapshots. It also automatically produces a set of key frames representing all the written content on the whiteboard before each erasure. The whiteboard content serves as a visual index to efficiently browse the audio meeting. The system not only captures the whiteboard content, but also helps the users to view and manage the captured meeting content efficiently and securely.
-
3.发明公开
公开(公告)号：EP1376467A3
公开(公告)日：2004-03-03
申请号：EP03012636.1
申请日：2003-06-03
Applicant: MICROSOFT CORPORATION
Inventor： Liu, Zicheng , Cohen, Michael
IPC: G06T3/00
CPC classification number: G06K9/00228 , G06T3/0062 , G06T5/006
Abstract: The present invention includes a real-time wide-angle image correction system and a method for alleviating distortion and perception problems in images captured by wide-angle cameras. In general, the real-time wide-angle image correction method generates warp table from pixel coordinates of a wide-angle image and applies the warp table to the wide-angle image to create a corrected wide-angle image. The corrections are performed using a parametric class of warping functions that include Spatially Varying Uniform (SVU) scaling functions. The SVU scaling functions and scaling factors are used to perform vertical scaling and horizontal scaling on the wide-angle image pixel coordinates. A horizontal distortion correction is performed using the SVU scaling functions at and at least two different scaling factors. This processing generates a warp table that can be applied to the wide-angle image to yield the corrected wide-angle image.
Abstract translation: 本发明包括实时广角图像校正系统和用于减轻广角相机拍摄的图像中的失真和感知问题的方法。 通常，实时广角图像校正方法根据广角图像的像素坐标生成翘曲表，并将该翘曲表应用于广角图像以创建校正后的广角图像。 使用包括空间变化均匀（SVU）缩放功能的参数类别的变形函数来执行校正。 SVU缩放函数和缩放因子用于在广角图像像素坐标上执行垂直缩放和水平缩放。 在至少两个不同的缩放因子处使用SVU缩放函数来执行水平失真校正。 该处理生成可应用于广角图像的翘曲表格以产生校正后的广角图像。
-
4.发明公开Method and apparatus for reducing noise corruption from an alternative sensor signal during multi-sensory speech enhancement 有权对于多感官语音增强期间减少的备选传感器信号的噪声劣化的方法和装置
公开(公告)号：EP1688919A1
公开(公告)日：2006-08-09
申请号：EP06100071.7
申请日：2006-01-04
Applicant: MICROSOFT CORPORATION
Inventor： Subramanya, Amarnag , Droppo, James G. , Zhang, Zhengyou , Liu, Zicheng
CPC classification number: G10L21/0208 , G10L2021/02165
Abstract: A method and apparatus classify a portion of an alternative sensor signal as either containing noise or not containing noise. The portions of the alternative sensor signal that are classified as containing noise are not used to estimate a portion of a clean speech signal and the channel response associated with the alternative sensor. The portions of the alternative sensor signal that are classified as not containing noise are used to estimate a portion of a clean speech signal and the channel response associated with the alternative sensor.
Abstract translation: 一种方法和装置归类为噪声要么含有或不含有噪声的备选传感器信号的一部分。 象包含噪声不被用于估计干净语音信号的一部分，并且与所述备选传感器相关联的所述信道响应中的备选传感器信号的部分被分类。 作为不包含噪声被用来估计干净语音信号的一部分，并且与所述备选传感器相关联的所述信道响应中的备选传感器信号的部分被分类。
-
5.发明公开Head mounted multi-sensory audio input system 有权Am Kopf angebrachtes Audioeingabesystem mit mehreren Sensoren
公开(公告)号：EP1503368A1
公开(公告)日：2005-02-02
申请号：EP04016226.5
申请日：2004-07-09
Applicant: MICROSOFT CORPORATION
Inventor： Huang, Xuedong D. , Liu, Zicheng , Zhang, Zhengyou , Sinclair, Michael J. , Acero, Alejandro
CPC classification number: H04R1/14 , G10L15/20 , G10L15/24 , G10L25/78 , H04R2460/13
Abstract: The present invention combines a conventional audio microphone with an additional speech sensor that provides a speech sensor signal based on an input. The speech sensor signal is generated based on an action undertaken by a speaker during speech, such as facial movement, bone vibration, throat vibration, throat impedance changes, etc. A speech detector component receives an input from the speech sensor and outputs a speech detection signal indicative of whether a user is speaking. The speech detector generates the speech detection signal based on the microphone signal and the speech sensor signal.
Abstract translation: 本发明将传统的音频麦克风与基于输入提供语音传感器信号的附加话音传感器相结合。 语音传感器信号基于语音中的扬声器在面部运动，骨骼振动，喉部振动，喉部阻抗变化等中的作用而产生。语音检测器组件从语音传感器接收输入并输出语音检测 指示用户是否在说话的信号。 语音检测器基于麦克风信号和语音传感器信号产生语音检测信号。
-
Patent Agency Ranking
公开(公告)号：EP2431972B1
公开(公告)日：2013-07-24
申请号：EP11008608.9
申请日：2004-10-26
Applicant: Microsoft Corporation
Inventor： Acero, Alejandro , Droppo, James G. , Sinclair, Michael J. , Huang, Xuedong David , Zhang, Zhengyou , Liu, Zicheng , Deng, Li , Zheng, Yanli
IPC: G10L21/02
CPC classification number: G10L21/0208 , G10L2021/02165
Abstract: A method and system use an alternative sensor signal received from a sensor other than an air conduction microphone to estimate a clean speech value. The estimation uses either the alternative sensor signal alone, or in conjunction with the air conduction microphone signal. The clean speech value is estimated without using a model trained from noisy training data collected from an air conduction microphone. Under one embodiment, correction vectors are added to a vector formed from the alternative sensor signal in order to form a filter, which is applied to the air conductive microphone signal to produce the clean speech estimate. In other embodiments, the pitch of a speech signal is determined from the alternative sensor signal and is used to decompose an air conduction microphone signal. The decomposed signal is then used to determine a clean signal estimate.
-
公开(公告)号：EP1503368B1
公开(公告)日：2010-06-16
申请号：EP04016226.5
申请日：2004-07-09
Applicant: MICROSOFT CORPORATION
Inventor： Huang, Xuedong D. , Liu, Zicheng , Zhang, Zhengyou , Sinclair, Michael J. , Acero, Alejandro
CPC classification number: H04R1/14 , G10L15/20 , G10L15/24 , G10L25/78 , H04R2460/13
-
公开(公告)号：EP1638084B1
公开(公告)日：2009-11-11
申请号：EP05107921.8
申请日：2005-08-30
Applicant: MICROSOFT CORPORATION
Inventor： Acero, Alejandro , Droppo, James G. , Huang, Xuedong David , Zhang, Zhengyou , Liu, Zicheng
IPC: G10L21/02
CPC classification number: H04R3/005 , G10L21/0208 , G10L2021/02161 , H04R2460/13
-
9.发明授权Method and apparatus for reducing noise corruption from an alternative sensor signal during multi-sensory speech enhancement 有权对于多感官语音增强期间减少的备选传感器信号的噪声劣化的方法和装置
公开(公告)号：EP1688919B1
公开(公告)日：2007-09-19
申请号：EP06100071.7
申请日：2006-01-04
Applicant: MICROSOFT CORPORATION
Inventor： Subramanya, Amarnag , Droppo, James G. , Zhang, Zhengyou , Liu, Zicheng
CPC classification number: G10L21/0208 , G10L2021/02165
-
10.发明公开Method and apparatus for multi-sensory speech enhancement on a mobile device 有权用于移动设备上的多感官语音增强的方法和设备
公开(公告)号：EP1648150A3
公开(公告)日：2006-05-31
申请号：EP05108871.4
申请日：2005-09-26
Applicant: MICROSOFT CORPORATION
Inventor： Sinclair, Michael , Granovetter, Randy Phyllis , Zhang, Zhengyou , Liu, Zicheng
IPC: H04M1/725
CPC classification number: H04M1/605 , G06F17/289 , G10L15/20 , G10L15/24 , G10L21/0208 , G10L2021/02161 , H04M1/05 , H04M1/6008 , H04M1/6066 , H04M1/7253 , H04M2250/02 , H04M2250/06 , H04M2250/10 , H04R1/083 , H04W88/02 , H04W92/18
Abstract: A mobile device (1300) includes an air conduction microphone and an alternative sensor that provides an alternative sensor signal indicative of speech. A communication interface permits the mobile device to communicate directly with other mobile devices (1302,1304).
Abstract translation: 移动设备（1300）包括气导麦克风和提供指示语音的替代传感器信号的替代传感器。 通信接口允许移动设备直接与其他移动设备（1302,1304）通信。
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.023 seconds)
