公开(公告)号：US09972313B2

公开(公告)日：2018-05-15

申请号：US15057695

申请日：2016-03-01

Applicant: Intel Corporation

Inventor： Tobias Bocklet ,  Adam Marek ,  Tomasz Dorau ,  Przemyslaw Sobon

IPC: G10L15/00 ,  G10L15/04 ,  G10L15/10 ,  G10L17/22 ,  G10L15/193 ,  G06F17/30 ,  G10L15/02

CPC classification number: G10L15/193 ,  G06F17/3053 ,  G06F17/30746 ,  G10L15/08 ,  G10L15/10 ,  G10L15/22 ,  G10L17/22 ,  G10L25/78 ,  G10L2015/025 ,  G10L2015/088 ,  G10L2015/223

Abstract: Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include intermediate scoring of a state or states of a key phrase model and/or a backward transition or rejection loopback from a state of the key phrase model to a rejection model to reduce false accepts based on received utterances.

公开(公告)号：US20160365096A1

公开(公告)日：2016-12-15

申请号：US15121004

申请日：2014-03-28

Applicant: INTEL CORPORATION

Inventor： Tobias Bocklet ,  Adam Marek

IPC: G10L17/04 ,  G10L17/16 ,  G10L17/08 ,  G10L17/02

CPC classification number: G10L17/04 ,  G10L17/02 ,  G10L17/08 ,  G10L17/16

Abstract: Various systems, apparatuses, and methods for training classifiers using selected cohort sample subsets are disclosed herein, in an example, a set of target supervectors, representing a target class, is received, and a set of cohort supervectors, representing a cohort class, is received. A distance metric is calculated from a respective cohort supervector to a respective target supervector, and a proper subset of cohort supervectors are selected based on the calculated distance metrics. The set of target supervectors and the selected proper subset of cohort supervectors are used to train a classifier. Further examples described herein describe how training classifiers using selected cohort sample subsets may be used to increase performance and decrease resource consumption in voice biometric systems.

Abstract translation: 在本文中公开了使用所选择的队列样本子集来训练分类器的各种系统，装置和方法，在一个示例中，接收到表示目标类的一组目标超向量，并且代表队列类的一组队列超向量是 收到了 从相应的队列超向量到相应的目标超向量计算距离度量，并且基于所计算的距离度量来选择队列超级向量的适当子集。 目标超级队员和选定的队列超级队员的子集用于训练分类器。 本文描述的进一步示例描述如何使用选择的队列样本子集的训练分类器可以用于增加语音生物测定系统中的性能并降低资源消耗。

公开(公告)号：US11715213B2

公开(公告)日：2023-08-01

申请号：US16914232

申请日：2020-06-26

Applicant: Intel Corporation

Inventor： Nelson Leung ,  Jonathan K. Lee ,  Bridget L. Williams ,  Sameer Sheorey ,  Amery Cong ,  Mehrnaz Khodam Hazrati ,  Sabar Mourad Souag ,  Adam Marek ,  Pawel Pieniazek ,  Bogna Bylicka ,  Jakub Powierza ,  Anna Banaszczyk-fiszer

IPC: G06V40/20 ,  G06T7/246 ,  G06T7/292 ,  G06T7/73 ,  G06V10/75 ,  G06V10/147 ,  G06V10/20 ,  G06V10/22 ,  G06V20/40 ,  G06V20/64

CPC classification number: G06T7/246 ,  G06T7/292 ,  G06T7/73 ,  G06V10/147 ,  G06V10/22 ,  G06V10/255 ,  G06V10/757 ,  G06V20/42 ,  G06V20/647 ,  G06V40/23 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30221

Abstract: Apparatus and methods for extraction and calculation of multi-person performance metrics in a three-dimensional space. An example apparatus includes a detector to identify a first subject in a first image captured by a first image capture device based on a first set of two-dimensional kinematic keypoints in the first image, the two-dimensional kinematic keypoints corresponding to a joint of the first subject, the first image capture device associated with a first view of the first subject, a multi-view associator to verify the first subject using the first image and a second image captured by a second image capture device, the second image capture device associated with a second view of the first subject, the second view different than the first view, and a keypoint generator to generate three-dimensional keypoints for the first subject using the first set of two-dimensional kinematic keypoints.

公开(公告)号：US20170200451A1

公开(公告)日：2017-07-13

申请号：US15128935

申请日：2014-07-04

Applicant: INTEL CORPORATION

Inventor： Tobias Bocklet ,  Adam Marek ,  Piotr Chlebek

IPC: G10L17/08 ,  G10L17/02 ,  G10L17/16 ,  G10L25/24

CPC classification number: G10L17/08 ,  G10L17/02 ,  G10L17/06 ,  G10L17/16 ,  G10L25/24

Abstract: Techniques related to detecting replay attacks on automatic speaker verification systems are discussed. Such techniques may include receiving an utterance from a user or a device playing back the utterance, determining features associated with the utterance, and classifying the utterance in a replay utterance class or an original utterance class based on a statistical classification or a margin classification of the utterance using the features.

公开(公告)号：US10038679B2

公开(公告)日：2018-07-31

申请号：US13726360

申请日：2012-12-24

Applicant: Intel Corporation

Inventor： Adam Marek

IPC: H04L29/06 ,  H04L9/32

CPC classification number: H04L63/062 ,  H04L9/3247 ,  H04L63/105 ,  H04L63/126 ,  H04L2209/127 ,  H04W12/003

Abstract: Various embodiments are generally directed to pairing computing devices for collaborative interaction via a network through a centralized secure device pairing service. An apparatus comprises a controller processor circuit, and a controller storage communicatively coupled to the controller processor circuit to store an initial private key and to store instructions that when executed by the controller processor circuit cause the controller processor circuit to create a first signature using the initial private key, transmit the first signature to an issuing server via a network, receive a group public key and an associated member private key from the issuing server, create a second signature using the member private key, transmit the second signature to a member device via the network; receive a third signature from the member device; and authenticate the third signature using the group public key. Other embodiments are described and claimed herein.