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

US08275622B2 Ultrasonic doppler sensor for speaker recognition 有权
标题翻译：超声多普勒传感器用于扬声器识别
公开(公告)号：US08275622B2
公开(公告)日：2012-09-25
申请号：US12366787
申请日：2009-02-06
申请人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
发明人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
IPC分类号： G10L15/00
CPC分类号： G10L17/00
摘要： A method and system recognizes an unknown speaker by directing an ultrasonic signal at a face of the unknown speaker. A Doppler signal of the ultrasonic signal is acquired after reflection by the face, and Doppler features are extracted from the reflected Doppler signal. The Doppler features are classified using Doppler models storing the Doppler features and identities of known speakers to recognize and identify the unknown speaker.
摘要翻译：方法和系统通过在未知扬声器的面部引导超声波信号来识别未知扬声器。在脸部反射之后获取超声波信号的多普勒信号，并从反射多普勒信号中提取多普勒特征。多普勒特征使用存储多普勒特征和已知扬声器的身份的多普勒模型进行分类，以识别和识别未知扬声器。

2. 发明授权

US08433892B2 Privacy-preserving probabilistic inference based on hidden Markov models 有权
标题翻译：基于隐马尔可夫模型的隐私保护概率推理
公开(公告)号：US08433892B2
公开(公告)日：2013-04-30
申请号：US13076410
申请日：2011-03-30
申请人： Shantanu Rane , Wei Sun , Manas A. Pathak , Bhiksha Raj
发明人： Shantanu Rane , Wei Sun , Manas A. Pathak , Bhiksha Raj
IPC分类号： H04L29/06
CPC分类号： H04L9/008 , G06N7/005 , H04L2209/46
摘要： A probability of an observation sequence stored at a client is evaluated securely with respect to a hidden Markov model (HMM) stored at a server. The server determines, for each state of the HMM, an encryption of a log-probability of a current element of the observation sequence. Determines, for each state of the HMM, an encryption of a log-summation of a product of a likelihood of the observation sequence based on a previous element of the observation sequence and a transition probability to the state of the HMM. Determines an encryption of a log-likelihood of the observation sequence for each state as a product of the encryption of a log-summation and an encryption of a corresponding log-probability of the current element of the observation sequence; and determines an encryption of the log-probability of the observation sequence based on the log-likelihood of the observation sequence for each state.
摘要翻译：相对于存储在服务器中的隐马尔可夫模型（HMM），安全地评估存储在客户端的观察序列的概率。对于HMM的每个状态，服务器确定观察序列的当前元素的对数概率的加密。确定对于HMM的每个状态，基于观测序列的先前元素和HMM状态的转移概率，对观测序列的可能性的乘积的对数加和进行加密。确定每个状态的观察序列的对数似然度的加密，作为对数求和的加密和观察序列的当前元素的相应对数概率的加密的乘积; 并且基于每个状态的观察序列的对数似然度来确定观察序列的对数概率的加密。

3. 发明申请

US20120254612A1 Privacy-Preserving Probabilistic Inference Based on Hidden Markov Models 有权
标题翻译：基于隐马尔可夫模型的隐私保护概率推理
公开(公告)号：US20120254612A1
公开(公告)日：2012-10-04
申请号：US13076410
申请日：2011-03-30
申请人： Shantanu Rane , Wei Sun , Manas A. Pathak , Bhiksha Raj
发明人： Shantanu Rane , Wei Sun , Manas A. Pathak , Bhiksha Raj
IPC分类号： G06N5/02 , H04L9/32
CPC分类号： H04L9/008 , G06N7/005 , H04L2209/46
摘要： A probability of an observation sequence stored at a client is evaluated securely with respect to a hidden Markov model (HMM) stored at a server. The server determines, for each state of the HMM, an encryption of a log-probability of a current element of the observation sequence. Determines, for each state of the HMM, an encryption of a log-summation of a product of a likelihood of the observation sequence based on a previous element of the observation sequence and a transition probability to the state of the HMM. Determines an encryption of a log-likelihood of the observation sequence for each state as a product of the encryption of a log-summation and an encryption of a corresponding log-probability of the current element of the observation sequence; and determines an encryption of the log-probability of the observation sequence based on the log-likelihood of the observation sequence for each state.
摘要翻译：相对于存储在服务器中的隐马尔可夫模型（HMM），安全地评估存储在客户端的观察序列的概率。对于HMM的每个状态，服务器确定观察序列的当前元素的对数概率的加密。确定对于HMM的每个状态，基于观测序列的先前元素和HMM状态的转移概率，对观测序列的可能性的乘积的对数加和进行加密。确定每个状态的观察序列的对数似然度的加密，作为对数求和的加密和观察序列的当前元素的相应对数概率的加密的乘积; 并且基于每个状态的观察序列的对数似然度来确定观察序列的对数概率的加密。

4. 发明申请

US20100204991A1 Ultrasonic Doppler Sensor for Speaker Recognition 有权
标题翻译：用于扬声器识别的超声多普勒传感器
公开(公告)号：US20100204991A1
公开(公告)日：2010-08-12
申请号：US12366787
申请日：2009-02-06
申请人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
发明人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
IPC分类号： G10L17/00 , G06K9/00
CPC分类号： G10L17/00
摘要： A method and system recognizes an unknown speaker by directing an ultrasonic signal at a face of the unknown speaker. A Doppler signal of the ultrasonic signal is acquired after reflection by the face, and Doppler features are extracted from the reflected Doppler signal. The Doppler features are classified using Doppler models storing the Doppler features and identities of known speakers to recognize and identify the unknown speaker.
摘要翻译：方法和系统通过在未知扬声器的面部引导超声波信号来识别未知扬声器。在脸部反射之后获取超声波信号的多普勒信号，并从反射多普勒信号中提取多普勒特征。多普勒特征使用存储多普勒特征和已知扬声器的身份的多普勒模型进行分类，以识别和识别未知扬声器。

5. 发明申请

US20100202656A1 Ultrasonic Doppler System and Method for Gesture Recognition 审中-公开
标题翻译：超声多普勒系统和手势识别方法
公开(公告)号：US20100202656A1
公开(公告)日：2010-08-12
申请号：US12367720
申请日：2009-02-09
申请人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
发明人： Bhiksha Raj Ramakrishnan , Kaustubh Kalgaonkar
IPC分类号： G06K9/00
CPC分类号： G06K9/00523 , G01S7/539 , G01S7/54 , G01S15/58 , G06F3/017 , G06K9/00335 , G06K9/6278
摘要： A method and system recognizes an unknown gesture by directing an ultrasonic signal at an object making an unknown gestures. A set of Doppler signals are acquired of the ultrasonic signal after reflection by the object. Doppler features are extracted from the reflected Doppler signal, and the Doppler features are classified using a set of Doppler models storing the Doppler features and identities of known gestures to recognize and identify the unknown gesture, wherein there is one Doppler model for each known gesture.
摘要翻译：方法和系统通过在产生未知手势的对象处引导超声波信号来识别未知姿态。在物体反射之后获取超声波信号的一组多普勒信号。从反射的多普勒信号中提取多普勒特征，并且使用存储多普勒特征和已知手势的身份的多普勒模型的一组多普勒特征来分类多普勒特征，以识别和识别未知手势，其中每个已知手势存在一个多普勒模型。

6. 发明授权

US07050969B2 Distributed speech recognition with codec parameters 失效
公开(公告)号：US07050969B2
公开(公告)日：2006-05-23
申请号：US09995179
申请日：2001-11-27
申请人： Bhiksha Raj , Joshua Midgal , Rita Singh
发明人： Bhiksha Raj , Joshua Midgal , Rita Singh
IPC分类号： G10L19/04
CPC分类号： G10L15/30 , G10L15/02 , G10L19/00
摘要： A method extracts speech recognition features from a speech signal coded as a bitstream. First, the bitstream is decoded to recover linear predictive coding filter parameters, and a residual signal. Then, the linear predictive coding filter parameters and the residual signal are discriminatively combined into speech recognition features.

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