公开(公告)号：US20180307981A1

公开(公告)日：2018-10-25

申请号：US15494826

申请日：2017-04-24

Applicant: Intel Corporation

Inventor： Gokcen Cilingir ,  Elmoustapha Ould-Ahmed-Vall ,  Rajkishore Barik ,  Kevin Nealis ,  Xiaoming Chen ,  Justin E. Gottschlich ,  Prasoonkumar Surti ,  Chandrasekaran Sakthivel ,  Abhishek R. Appu ,  John C. Weast ,  Sara S. Baghsorkhi ,  Barnan Das ,  Narayan Biswal ,  Stanley J. Baran ,  Nilesh Shah ,  Archie Sharma ,  Mayuresh M. Varerkar

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F9/3001 ,  G06F9/3017 ,  G06F9/3851 ,  G06F9/3887 ,  G06F9/3895 ,  G06F9/46 ,  G06N3/04 ,  G06N3/063 ,  G06T1/20

Abstract: An apparatus to facilitate neural network (NN) training is disclosed. The apparatus includes training logic to receive one or more network constraints and train the NN by automatically determining a best network layout and parameters based on the network constraints.

公开(公告)号：US11862176B2

公开(公告)日：2024-01-02

申请号：US17327379

申请日：2021-05-21

Applicant: Intel Corporation

Inventor： Gokcen Cilingir ,  Narayan Biswal

IPC: G10L15/20 ,  G10L17/04 ,  G10L17/12 ,  G10L17/20 ,  G10L21/0208 ,  G10L17/06

CPC classification number: G10L17/04 ,  G10L17/06 ,  G10L17/12 ,  G10L17/20 ,  G10L21/0208 ,  G10L2021/02082

Abstract: Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user.

公开(公告)号：US11487811B2

公开(公告)日：2022-11-01

申请号：US16696854

申请日：2019-11-26

Applicant: Intel Corporation

Inventor： Barnan Das ,  Mayuresh M. Varerkar ,  Narayan Biswal ,  Stanley J. Baran ,  Gokcen Cilingir ,  Nilesh V. Shah ,  Archie Sharma ,  Sherine Abdelhak ,  Praneetha Kotha ,  Neelay Pandit ,  John C. Weast ,  Mike B. MacPherson ,  Dukhwan Kim ,  Linda L. Hurd ,  Abhishek R. Appu ,  Altug Koker ,  Joydeep Ray

IPC: G06F16/583 ,  G06F16/783 ,  G06K9/62 ,  G06V10/94 ,  G06V40/10 ,  G06V40/20

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

公开(公告)号：US20220036903A1

公开(公告)日：2022-02-03

申请号：US17327379

申请日：2021-05-21

Applicant: Intel Corporation

Inventor： Gokcen Cilingir ,  Narayan Biswal

IPC: G10L17/04 ,  G10L17/12 ,  G10L17/20 ,  G10L21/0208 ,  G10L17/06

Abstract: Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user.

公开(公告)号：US11178373B2

公开(公告)日：2021-11-16

申请号：US16050322

申请日：2018-07-31

Applicant: Intel Corporation

Inventor： Mayuresh Varerkar ,  Stanley Baran ,  Michael Apodaca ,  Prasoonkumar Surti ,  Atsuo Kuwahara ,  Narayan Biswal ,  Jill Boyce ,  Yi-Jen Chiu ,  Gokcen Cilingir ,  Barnan Das ,  Atul Divekar ,  Srikanth Potluri ,  Nilesh Shah ,  Archie Sharma

IPC: H04H60/33 ,  H04N13/111 ,  H04N19/597 ,  G06F9/38 ,  G06F3/01 ,  G06N20/00

Abstract: A mechanism is described for facilitating adaptive resolution and viewpoint-prediction for immersive media in computing environments. An apparatus of embodiments, as described herein, includes one or more processors to receive viewing positions associated with a user with respect to a display, and analyze relevance of media contents based on the viewing positions, where the media content includes immersive videos of scenes captured by one or more cameras. The one or more processors are further to predict portions of the media contents as relevant portions based on the viewing positions and transmit the relevant portions to be rendered and displayed.

公开(公告)号：US11017781B2

公开(公告)日：2021-05-25

申请号：US16153756

申请日：2018-10-06

Applicant: INTEL CORPORATION

Inventor： Gokcen Cilingir ,  Narayan Biswal

IPC: G10L15/00 ,  G10L15/16 ,  G10L17/04 ,  G10L17/12 ,  G10L17/20 ,  G10L21/0208 ,  G10L17/06

Abstract: Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user.

公开(公告)号：US20190279645A1

公开(公告)日：2019-09-12

申请号：US16153756

申请日：2018-10-06

Applicant: INTEL CORPORATION

Inventor： Gokcen Cilingir ,  Narayan Biswal

IPC: G10L17/04 ,  G10L17/06 ,  G10L17/20 ,  G10L17/12 ,  G10L21/0208

Abstract: Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user.

公开(公告)号：US10339935B2

公开(公告)日：2019-07-02

申请号：US15626828

申请日：2017-06-19

Applicant: INTEL CORPORATION

Inventor： Gokcen Cilingir ,  Jonathan J. Huang ,  Narayan Biswal ,  Mandar S. Joshi

IPC: G10L15/20 ,  G10L17/04 ,  G10L17/22 ,  G10L17/06 ,  G10L15/02 ,  G10L25/60

Abstract: Techniques are provided for training of a text independent (TI) speaker recognition (SR) model. A methodology implementing the techniques according to an embodiment includes measuring context data associated with collected TI speech utterances from a user and identifying the user based on received identity measurements. The method further includes performing a speech quality analysis and a speaker state analysis based on the utterances, and evaluating a training merit value of the utterances, based on the speech quality analysis and the speaker state analysis. If the training merit value exceeds a threshold value, the utterances are stored as training data in a training database. The database is indexed by the user identity and the context data. The method further includes determining whether the stored training data has achieved a sufficiency level for enrollment of a TI SR model, and training the TI SR model for the identified user and context.

公开(公告)号：US10242486B2

公开(公告)日：2019-03-26

申请号：US15488837

申请日：2017-04-17

Applicant: Intel Corporation

Inventor： Chandrasekaran Sakthivel ,  Michael Apodaca ,  Kai Xiao ,  Altug Koker ,  Jeffery S. Boles ,  Adam T. Lake ,  Nikos Kaburlasos ,  Joydeep Ray ,  John H. Feit ,  Travis T. Schluessler ,  Jacek Kwiatkowski ,  James M. Holland ,  Prasoonkumar Surti ,  Jonathan Kennedy ,  Louis Feng ,  Barnan Das ,  Narayan Biswal ,  Stanley J. Baran ,  Gokcen Cilingir ,  Nilesh V. Shah ,  Archie Sharma ,  Mayuresh M. Varerkar

IPC: G06T15/06 ,  G06T15/00 ,  G06T19/00 ,  G06F3/01 ,  H04S7/00 ,  G06T15/04 ,  G06T15/80 ,  G06T17/10

Abstract: Systems, apparatuses and methods may provide away to render augmented reality and virtual reality (VR/AR) environment information. More particularly, systems, apparatuses and methods may provide a way to selectively suppress and enhance VR/AR renderings of n-dimensional environments. The systems, apparatuses and methods may deepen a user's VR/AR experience by focusing on particular feedback information, while suppressing other feedback information from the environment.

公开(公告)号：US10108850B1

公开(公告)日：2018-10-23

申请号：US15495327

申请日：2017-04-24

Applicant: Intel Corporation

Inventor： Barnan Das ,  Mayuresh M. Varerkar ,  Narayan Biswal ,  Stanley J. Baran ,  Gokcen Cilingir ,  Nilesh V. Shah ,  Archie Sharma ,  Sherine Abdelhak ,  Praneetha Kotha ,  Neelay Pandit ,  John C. Weast ,  Mike B. Macpherson ,  Dukhwan Kim ,  Linda L. Hurd ,  Abhishek R. Appu ,  Altug Koker ,  Joydeep Ray

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/70 ,  G06F17/30

CPC classification number: G06K9/00288 ,  G06F17/30256 ,  G06F17/30793 ,  G06K9/00255 ,  G06K9/00268 ,  G06K9/00885 ,  G06K9/6269 ,  G06T7/70 ,  G06T2207/30184 ,  G06T2207/30201 ,  G06T2207/30232

Abstract: A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.