专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08375030B2 Differentially private aggregate classifier for multiple databases 有权
标题翻译：用于多个数据库的差异化私有聚合分类器
公开(公告)号：US08375030B2
公开(公告)日：2013-02-12
申请号：US12960221
申请日：2010-12-03
申请人： Shantanu Rane , Manas A. Pathak , Bhiksha Ramakrishnan
发明人： Shantanu Rane , Manas A. Pathak , Bhiksha Ramakrishnan
IPC分类号： G06F17/30
CPC分类号： G06F17/30539 , G06F21/6245 , G06Q10/00
摘要： Embodiments of the invention disclose a system and a method for determining a differentially private aggregate classifier for a set of databases, wherein each database in the set of databases is associated with a classifier and a noise value, wherein the classifier and the noise value are determined locally for each database, such that a combination of the classifier and the noise value ensure a differential data privacy of the database, and wherein the differentially private aggregate classifier preserves the differential data privacy of each database. The differentially private aggregate classifier is a combination of the classifiers of the set of databases modified with the noise value corresponding to a smallest database in the set of databases.
摘要翻译：本发明的实施例公开了一种用于确定一组数据库的差分私有聚类分类器的系统和方法，其中数据库集合中的每个数据库与分类器和噪声值相关联，其中分类器和噪声值被确定本地为每个数据库，使得分类器和噪声值的组合确保数据库的差异数据隐私，并且其中差异化私有聚合分类器保留每个数据库的差分数据隐私。差异化私有聚合分类器是用数据库集中的最小数据库对应的噪声值修改的数据库集合的分类器的组合。

2. 发明申请

US20120143922A1 Differentially private aggregate classifier for multiple databases 有权
标题翻译：用于多个数据库的差异化私有聚合分类器
公开(公告)号：US20120143922A1
公开(公告)日：2012-06-07
申请号：US12960221
申请日：2010-12-03
申请人： Shantanu Rane , Manas A. Pathak , Bhiksha Ramakrishnan
发明人： Shantanu Rane , Manas A. Pathak , Bhiksha Ramakrishnan
IPC分类号： G06F17/30
CPC分类号： G06F17/30539 , G06F21/6245 , G06Q10/00
摘要： Embodiments of the invention disclose a system and a method for determining a differentially private aggregate classifier for a set of databases, wherein each database in the set of databases is associated with a classifier and a noise value, wherein the classifier and the noise value are determined locally for each database, such that a combination of the classifier and the noise value ensure a differential data privacy of the database, and wherein the differentially private aggregate classifier preserves the differential data privacy of each database. The differentially private aggregate classifier is a combination of the classifiers of the set of databases modified with the noise value corresponding to a smallest database in the set of databases.
摘要翻译：本发明的实施例公开了一种用于确定一组数据库的差分私有聚类分类器的系统和方法，其中数据库集合中的每个数据库与分类器和噪声值相关联，其中分类器和噪声值被确定本地为每个数据库，使得分类器和噪声值的组合确保数据库的差异数据隐私，并且其中差异化私有聚合分类器保留每个数据库的差分数据隐私。差异化私有聚合分类器是用数据库集中的最小数据库对应的噪声值修改的数据库集合的分类器的组合。

3. 发明授权

US08015003B2 Denoising acoustic signals using constrained non-negative matrix factorization 有权
标题翻译：使用约束非负矩阵分解来去噪声信号
公开(公告)号：US08015003B2
公开(公告)日：2011-09-06
申请号：US11942015
申请日：2007-11-19
申请人： Kevin W. Wilson , Ajay Divakaran , Bhiksha Ramakrishnan , Paris Smaragdis
发明人： Kevin W. Wilson , Ajay Divakaran , Bhiksha Ramakrishnan , Paris Smaragdis
IPC分类号： G10L21/06
CPC分类号： G10L21/0208 , G10L21/02 , G10L21/0232 , G10L21/0272
摘要： A method and system denoises a mixed signal. A constrained non-negative matrix factorization (NMF) is applied to the mixed signal. The NMF is constrained by a denoising model, in which the denoising model includes training basis matrices of a training acoustic signal and a training noise signal, and statistics of weights of the training basis matrices. The applying produces weight of a basis matrix of the acoustic signal of the mixed signal. A product of the weights of the basis matrix of the acoustic signal and the training basis matrices of the training acoustic signal and the training noise signal is taken to reconstruct the acoustic signal. The mixed signal can be speech and noise.
摘要翻译：一种方法和系统去除混合信号。受限的非负矩阵分解（NMF）被应用于混合信号。 NMF由去噪模型约束，其中去噪模型包括训练声信号和训练噪声信号的训练基矩阵，以及训练基矩阵的权重统计。该应用产生混合信号的声信号的基矩阵的权重。采用声信号的基矩阵的权重和训练声信号的训练基矩阵和训练噪声信号的乘积来重构声信号。混合信号可以是语音和噪声。

4. 发明授权

US07372770B2 Ultrasonic Doppler sensor for speech-based user interface 有权
标题翻译：超声多普勒传感器，用于基于语音的用户界面
公开(公告)号：US07372770B2
公开(公告)日：2008-05-13
申请号：US11519372
申请日：2006-09-12
申请人： Bhiksha Ramakrishnan , Kaustubh Kalgaonkar
发明人： Bhiksha Ramakrishnan , Kaustubh Kalgaonkar
IPC分类号： G01S15/02
CPC分类号： G10L25/78
摘要： A method and system detect speech activity. An ultrasonic signal is directed at a face of a speaker over time. A Doppler signal of the ultrasonic signal is acquired after reflection by the face. Energy in the Doppler signal is measured over time. The energy over time is compared to a predetermined threshold to detect speech activity of the speaker in a concurrently acquired audio signal.
摘要翻译：一种方法和系统检测语音活动。随着时间的推移，超声信号被指向扬声器的一面。超声波信号的多普勒信号由面部反射后获取。随着时间的推移测量多普勒信号中的能量。将时间的能量与预定阈值进行比较，以检测并发获取的音频信号中的扬声器的语音活动。

5. 发明授权

US07792314B2 System and method for acquiring acoustic signals using doppler techniques 有权
标题翻译：使用多普勒技术获取声信号的系统和方法
公开(公告)号：US07792314B2
公开(公告)日：2010-09-07
申请号：US11110396
申请日：2005-04-20
申请人： Bhiksha Ramakrishnan , Paul H. Dietz , Bent Schmidt-Nielsen
发明人： Bhiksha Ramakrishnan , Paul H. Dietz , Bent Schmidt-Nielsen
IPC分类号： H04B15/00
CPC分类号： G10L21/0208 , G10L15/20 , H04B7/01 , H04B17/391
摘要： A method and system enhances an acoustic signal acquired by a microphone from an acoustic source while concurrently acquiring a Doppler signal from moving parts of the acoustic source. The acoustic signal and the Doppler signal are then analyzed according to a model to generate an enhanced acoustic signal.
摘要翻译：一种方法和系统从声源增强由麦克风获取的声学信号，同时从声源的运动部分获取多普勒信号。然后根据模型分析声信号和多普勒信号以产生增强的声信号。

6. 发明授权

US07698143B2 Constructing broad-band acoustic signals from lower-band acoustic signals 失效
标题翻译：从低频声信号构建宽带声信号
公开(公告)号：US07698143B2
公开(公告)日：2010-04-13
申请号：US11130735
申请日：2005-05-17
申请人： Bhiksha Ramakrishnan , Paris Smaragdis
发明人： Bhiksha Ramakrishnan , Paris Smaragdis
IPC分类号： G10L19/00 , G10L19/02
CPC分类号： G10L21/038
摘要： A method generates envelope spectra and harmonic spectra from an input broad-band training acoustic signal. Corresponding non-negative envelope bases are trained for the envelope spectra and non-negative harmonic bases are trained for the harmonic spectra using convolutive non-negative matrix factorization. Higher-band frequencies are generated for an input lower-band acoustic signal according to the non-negative envelope bases and the non-negative harmonic bases. Then, the input lower-band acoustic signal is combined with the higher-band frequencies to produce an output broad-band acoustic signal.
摘要翻译：一种方法从输入宽带训练声信号产生包络谱和谐波谱。针对包络谱对相应的非负包络基进行训练，使用卷积非负矩阵因式分解对非谐波基进行了谐波谱训练。根据非负包络线和非负谐波基，为输入低频声信号产生较高频带频率。然后，输入低频声信号与较高频带频率组合以产生输出宽带声信号。

7. 发明申请

US20080071532A1 ULTRASONIC DOPPLER SENSOR FOR SPEECH-BASED USER INTERFACE 有权
标题翻译：用于基于语音用户界面的超声波多普勒传感器
公开(公告)号：US20080071532A1
公开(公告)日：2008-03-20
申请号：US11519372
申请日：2006-09-12
申请人： Bhiksha Ramakrishnan , Kaustubh Kalgaonkar
发明人： Bhiksha Ramakrishnan , Kaustubh Kalgaonkar
IPC分类号： G10L15/20 , G01S15/00 , G08B23/00
CPC分类号： G10L25/78
摘要： A method and system detect speech activity. An ultrasonic signal is directed at a face of a speaker over time. A Doppler signal of the ultrasonic signal is acquired after reflection by the face. Energy in the Doppler signal is measured over time. The energy over time is compared to a predetermined threshold to detect speech activity of the speaker in a concurrently acquired audio signal.
摘要翻译：一种方法和系统检测语音活动。随着时间的推移，超声信号被指向扬声器的一面。超声波信号的多普勒信号由面部反射后获取。随着时间的推移测量多普勒信号中的能量。将时间的能量与预定阈值进行比较，以检测并发获取的音频信号中的扬声器的语音活动。

8. 发明申请

US20060265210A1 Constructing broad-band acoustic signals from lower-band acoustic signals 失效
标题翻译：从低频声信号构建宽带声信号
公开(公告)号：US20060265210A1
公开(公告)日：2006-11-23
申请号：US11130735
申请日：2005-05-17
申请人： Bhiksha Ramakrishnan , Paris Smaragdis
发明人： Bhiksha Ramakrishnan , Paris Smaragdis
IPC分类号： G10L19/14 , G10L21/00
CPC分类号： G10L21/038
摘要： A method generates envelope spectra and harmonic spectra from an input broad-band training acoustic signal. Corresponding non-negative envelope bases are trained for the envelope spectra and non-negative harmonic bases are trained for the harmonic spectra using convolutive non-negative matrix factorization. Higher-band frequencies are generated for an input lower-band acoustic signal according to the non-negative envelope bases and the non-negative harmonic bases. Then, the input lower-band acoustic signal is combined with the higher-band frequencies to produce an output broad-band acoustic signal.
摘要翻译：一种方法从输入宽带训练声信号产生包络谱和谐波谱。针对包络谱对相应的非负包络基进行训练，使用卷积非负矩阵因式分解对非谐波基进行了谐波谱训练。根据非负包络线和非负谐波基，为输入低频声信号产生较高频带频率。然后，输入低频声信号与较高频带频率组合以产生输出宽带声信号。

9. 发明申请

US20050259149A1 Surveillance system with acoustically augmented video monitoring 审中-公开
标题翻译：具有声学增强视频监控的监控系统
公开(公告)号：US20050259149A1
公开(公告)日：2005-11-24
申请号：US10852382
申请日：2004-05-24
申请人： Paris Smaragdis , Bhiksha Ramakrishnan
发明人： Paris Smaragdis , Bhiksha Ramakrishnan
IPC分类号： G08B13/196 , H04N5/445 , H04N7/18
CPC分类号： G08B13/19695 , G08B13/19645 , G08B13/19691
摘要： A system and method includes visualizing acoustic activity, or its detected features, and displaying the acoustic activity as visual signals alongside videos acquired by cameras. Either through use of simple signal processing, or through use of more sophisticated audio analysis or sound recognition, useful information can be extracted from acoustic signals. The extracted information can be transformed to visual signals superimposed on the video signals acquired by the cameras.
摘要翻译：系统和方法包括将声学活动或其检测到的特征可视化，并且将声学活动显示为视觉信号以及由相机获取的视频。无论是通过使用简单的信号处理，还是通过使用更复杂的音频分析或声音识别，可以从声学信号中提取有用的信息。所提取的信息可以被转换成叠加在摄像机获得的视频信号上的视觉信号。

10. 发明授权

US07821870B2 Method and system for identifying moving objects using acoustic signals 有权
标题翻译：使用声信号识别移动物体的方法和系统
公开(公告)号：US07821870B2
公开(公告)日：2010-10-26
申请号：US11208463
申请日：2005-08-19
申请人： Bhiksha Ramakrishnan
发明人： Bhiksha Ramakrishnan
IPC分类号： G01S15/04 , G01S13/04 , G01S15/00 , G01S13/00
CPC分类号： G01S7/415 , G01S7/539
摘要： An acoustic tone at a predetermined frequency is detected after being reflected and modulated by an unknown moving object. Acoustic features are extracted from the reflected acoustic tone using acoustic spectral analysis. A dimensionality of the acoustic features is reduced, and the reduced dimensionality features are statistically classified to identify the object.
摘要翻译：在由未知的移动物体反射和调制之后，检测出预定频率的声音。使用声谱分析从反射的声学音调中提取声学特征。降低了声学特征的维数，并且对维度特征进行了统计分类，以识别对象。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式