Patents Examined by Yosef K Laekemariam
  • Patent number: 11638104
    Abstract: An ear-worn electronic device comprises a plurality of EEG sensors configured to sense EEG signals from or proximate a wearer's ear. At least one processor is configured to detect, during a baseline period of no wearer movement, EEG signals from the EEG sensors, and detect, during each of a plurality of candidate control movements by the wearer, EEG signals from the EEG sensors. The at least one processor is also configured to compute, using the EEG signals, discriminability metrics for the candidate control movements and the baseline period, the discriminability metrics indicating how discriminable neural signals associated with the candidate control movements and the baseline period are from one another. The at least one processor is further configured to select a subset of the candidate control movements using the discriminability metrics, each of the selected control movements defining a neural command for controlling the ear-worn electronic device by the wearer.
    Type: Grant
    Filed: July 15, 2021
    Date of Patent: April 25, 2023
    Assignee: Starkey Laboratories, Inc.
    Inventors: Lauren Petley, Swapan Gandhi, Simon Carlile, Sahar Akram
  • Patent number: 11628767
    Abstract: A method of playing a virtual after-burn sound in an electric vehicle is provided. The method includes acquiring driver tendency information generated based on information of music played in a mobile phone and collecting driving variable information for playing a virtual sound during operation of the electric vehicle. Additionally, characteristics of a virtual after-burn sound are determined based on the collected driving variable information. The characteristics of the virtual after-burn sound are corrected according to the acquired driver tendency information. An after-burn signal is generated for playing the virtual after-burn sound based on information about the corrected characteristics of the virtual after-burn sound and operation of sound equipment is adjusted according to the created after-burn signal such that a virtual after-burn sound discriminated according to the driver tendency is played and output from the sound equipment.
    Type: Grant
    Filed: March 30, 2021
    Date of Patent: April 18, 2023
    Assignees: Hyundai Motor Company, Kia Motors Corporation
    Inventors: Ki Chang Kim, Jin Sung Lee, Jeong Soo Eo, Dong Chul Park, Tae Kun Yun, Ji Won Oh
  • Patent number: 11632641
    Abstract: An apparatus for playing back an audio object associated with a position includes a distance calculator for calculating distances of the position to speakers or for reading the distances of the position to the speakers. The distance calculator is configured to take a solution with a smallest distance. The apparatus is configured to play back the audio object using the speaker corresponding to the solution.
    Type: Grant
    Filed: February 19, 2020
    Date of Patent: April 18, 2023
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Simone Neukam, Jan Plogsties, Max Neuendorf, Juergen Herre, Bernhard Grill
  • Patent number: 11625602
    Abstract: A method may include training, based on a first training dataset, a machine learning model. A degradation of the machine learning model may be detected based on one or more accuracy key performance indicators including a prediction power metric and a prediction confidence metric. The degradation of the machine learning model may also be detected based on a drift and skew in an input dataset and/or an output dataset of the machine learning model. Furthermore, the degradation of the machine learning model may be detected based on an explicit feedback and/or an implicit feedback on a performance of the machine learning model. In response to detecting the degradation of the machine learning model, the machine learning model may be retrained based on a second training dataset that includes at least one training sample not included in the first training dataset. Related systems and articles of manufacture are also provided.
    Type: Grant
    Filed: September 11, 2019
    Date of Patent: April 11, 2023
    Assignee: SAP SE
    Inventor: Siar Sarferaz
  • Patent number: 11627429
    Abstract: An apparatus, method and computer program product for: providing spatial audio signals for output for a first user via a first audio device and a second audio device, receiving an indication of deactivation of the second audio device, receiving an indication that the second audio device is re-activated by a second user, and performing, in response to receiving the indication that the second audio device is re-activated by the second user, a modification of the spatial audio signals.
    Type: Grant
    Filed: March 22, 2021
    Date of Patent: April 11, 2023
    Assignee: Nokia Technologies Oy
    Inventors: Lasse Juhani Laaksonen, Jussi Artturi Leppänen, Arto Juhani Lehtiniemi, Miikka Tapani Vilermo
  • Patent number: 11616903
    Abstract: A method for assisting a user, who is looking at a screen of a user device, to focus on a camera region of the screen includes receiving image data of the user, the image data being captured by a camera of the user device arranged to the screen close to the camera region; determining user input data indicative of that the user wants assistance to focus on the camera region; determining, based on the user input, gaze tracking data of the user looking at the screen, wherein the gaze tracking data are representative for a gaze area on the screen, at which the user is looking at a time of the user input or shortly before the user input; and displaying a screen content in the gaze area of the screen in the camera region.
    Type: Grant
    Filed: February 5, 2021
    Date of Patent: March 28, 2023
    Assignee: 4tiitoo GmbH
    Inventors: Tore Meyer, Stephan Odorfer
  • Patent number: 11607170
    Abstract: A system may obtain a set of features characterizing a segment of inertial measurement unit (IMU) data generated by an IMU of an ear-wearable device. The system may apply a machine learning model (MLM) that takes the features characterizing the segment of the IMU data as input. The system may determine, based on output values produced by the MLM, whether a user of the ear-wearable device has potentially been subject to physical abuse. The system may then perform an action in response to determining that the user of the ear-wearable device has potentially been subject to physical abuse.
    Type: Grant
    Filed: January 30, 2020
    Date of Patent: March 21, 2023
    Assignee: Starkey Laboratories, Inc.
    Inventors: Matan Sivan, Nitzan Bornstein, Justin Burwinkel, Roy Talman, Neta Aviel
  • Patent number: 11611720
    Abstract: The present invention discloses a display device and a manufacturing method thereof, the display device has a camera region and a displaying region surrounding the camera region, and has a cover plate; a transparent release agent layer disposed on the cover plate and is located in the camera region; a display function structural layer disposed on a surface of the cover plate with the transparent release agent layer; a protective adhesive layer disposed on the display function structural layer, and the protective adhesive layer having a first through hole corresponding to a region of the transparent release agent layer; the display function structural layer having a second through hole corresponding to the region of the transparent release agent layer.
    Type: Grant
    Filed: November 7, 2019
    Date of Patent: March 21, 2023
    Assignee: Wuhan China Star Optoelectronics Semiconductor Display Technology Co., Ltd.
    Inventors: Yong Zhao, Zuomin Liao, Tao Chen
  • Patent number: 11610118
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent interacting with an environment. In one aspect, a method comprises: receiving a current observation; for each action of a plurality of actions: randomly sampling one or more probability values; for each probability value: processing the action, the current observation, and the probability value using a quantile function network to generate an estimated quantile value for the probability value with respect to a probability distribution over possible returns that would result from the agent performing the action in response to the current observation; determining a measure of central tendency of the one or more estimated quantile values; and selecting an action to be performed by the agent in response to the current observation using the measures of central tendency for the actions.
    Type: Grant
    Filed: February 11, 2019
    Date of Patent: March 21, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Georg Ostrovski, William Clinton Dabney
  • Patent number: 11600951
    Abstract: The present invention relates to methods and systems for minimizing alien crosstalk between connectors. Specifically, the methods and systems relate to isolation and compensation techniques for minimizing alien crosstalk between connectors for use with high-speed data cabling. A frame can be configured to receive a number of connectors. Shield structures may be positioned to isolate at least a subset of the connectors from one another. The connectors can be positioned to move at least a subset of the connectors away from alignment with a common plane. A signal compensator may be configured to adjust a data signal to compensate for alien crosstalk. The connectors are configured to efficiently and accurately propagate high-speed data signals by, among other functions, minimizing alien crosstalk.
    Type: Grant
    Filed: June 30, 2021
    Date of Patent: March 7, 2023
    Assignee: CommScope Technologies LLC
    Inventor: Bernard Harold Hammond, Jr.
  • Patent number: 11601772
    Abstract: Systems and methods for using auditorily-induced vection (AIV) to enhance a person's attitude awareness are provided herein. In at least one embodiment, an auditory object is projected based on the orientation of the person or a vehicle and the projected auditory is provided to the person. By projecting the auditory object, the attitude of the person or the vehicle can be conveyed to the person to enhance the person's attitude awareness.
    Type: Grant
    Filed: September 11, 2019
    Date of Patent: March 7, 2023
    Assignee: Raytheon BBN Technologies Corp.
    Inventor: Scott E. Ritter
  • Patent number: 11588981
    Abstract: There is provided a control apparatus. A first acquiring unit acquires a user instruction identified through voice recognition. A determining unit determines a current state of an image capturing apparatus. In response to a first user instruction being acquired as the user instruction, a control unit: controls the image capturing apparatus to perform first processing in a case where the current state is a shooting state; and controls the image capturing apparatus to perform second processing in a case where the current state is a playback/display state or a menu display state.
    Type: Grant
    Filed: October 20, 2020
    Date of Patent: February 21, 2023
    Assignee: Canon Kabushiki Kaisha
    Inventor: Rurika Shimizu
  • Patent number: 11589159
    Abstract: The present embodiments generally relate to enabling participants in an online gathering with networked audio to use a cancelling auralizer at their respective locations to create a common acoustic space or set of acoustic spaces shared among subgroups of participants. For example, there are a set of network connected nodes, and the nodes can contain speakers and microphones, as well as participants and node mixing-processing blocks. The node mixing-processing blocks generate and manipulate signals for playback over the node loudspeakers and for distribution to and from the network. This processing can include cancellation of loudspeaker signals from the microphone signals and auralization of signals according to control parameters that are developed locally and from the network.
    Type: Grant
    Filed: October 19, 2020
    Date of Patent: February 21, 2023
    Assignees: The Board of Trustees of the Leland Stanford Junior University, University of Limerick
    Inventors: Jonathan S. Abel, Eoin F. Callery
  • Patent number: 11586280
    Abstract: Embodiments are disclosed for head motion prediction for spatial audio applications. In an embodiment, a method comprises: obtaining motion data from a source device and a headset; obtaining transmission delays from a wireless stack of the source; estimating relative motion from the relative source device and headset motion data; calculating a first derivative of the relative motion data; forward predicting the estimated relative motion over the time delays using the first derivative and second derivative of relative motion; determining, using a head tracker, a head pose of the user based on the forward predicted relative motion data; and rendering, using the head pose, spatial audio for playback on the headset.
    Type: Grant
    Filed: June 17, 2021
    Date of Patent: February 21, 2023
    Assignee: Apple Inc.
    Inventors: Evan G. Kriminger, Xiaoyuan Tu, Alexander Singh Alvarado
  • Patent number: 11589002
    Abstract: A webcam apparatus, having a display surface characterized by a display area, includes an image capture device characterized by an optical axis and a first footprint in a plane perpendicular to the optical axis; and an energy transfer device with a first portion coupled to the image capture device; and a second portion allowing attachment to an edge of a display screen. When attached, the image capture device and the first portion lie against and in contact with the display surface, or in a proximate and parallel plane. An optical axis characterizing the image capture device is aligned with a gaze direction of a user addressing a viewer via the captured images. The first portion of the energy transfer device is transparent at optical wavelengths, and has a second footprint in the plane perpendicular to the optical axis. The first and second footprints are small relative to the display area.
    Type: Grant
    Filed: November 8, 2021
    Date of Patent: February 21, 2023
    Inventors: Barbara Baney, Douglas M Baney
  • Patent number: 11580383
    Abstract: A large amount of training data is typically required to perform deep network leaning, making it difficult to achieve using a few pieces of data. In order to solve this problem, the neural network device according to the present invention is provided with: a feature extraction unit which extracts features from training data using a learning neural network; an adversarial feature generation unit which generates an adversarial feature from the extracted features using the learning neural network; a pattern recognition unit which calculates a neural network recognition result using the training data and the adversarial feature; and a network learning unit which performs neural network learning so that the recognition result approaches a desired output.
    Type: Grant
    Filed: March 16, 2017
    Date of Patent: February 14, 2023
    Assignee: NEC CORPORATION
    Inventor: Masato Ishii
  • Patent number: 11570565
    Abstract: An apparatus comprising means for: simultaneously controlling content rendered by a hand portable device and content rendered by a spatial audio device; and providing for rendering to a user, in response to an action by the user, of a first part, not a second part, of a spatial audio content via the hand portable device not the spatial audio device.
    Type: Grant
    Filed: September 5, 2019
    Date of Patent: January 31, 2023
    Assignee: Nokia Technologies Oy
    Inventors: Sujeet Shyamsundar Mate, Arto Lehtiniemi, Antti Eronen, Lasse Laaksonen
  • Patent number: 11568243
    Abstract: A processor-implemented method of performing convolution operations in a neural network includes generating a plurality of first sub-bit groups and a plurality of second sub-bit groups, respectively from at least one pixel value of an input feature map and at least one predetermined weight, performing a convolution operation on a first pair that includes a first sub-bit group including a most significant bit (MSB) of the at least one pixel value and a second sub-bit group including an MSB of the at least one predetermined weight, based on the plurality of second sub-bit groups, obtaining a maximum value of a sum of results for convolution operations of remaining pairs excepting the first pair, and based on a result of the convolution operation on the first pair and the maximum value, determining whether to perform the convolution operations of the remaining pairs.
    Type: Grant
    Filed: December 5, 2019
    Date of Patent: January 31, 2023
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Joonho Song, Namjoon Kim, Sehwan Lee, Deokjin Joo
  • Patent number: 11558562
    Abstract: Disclosed is a method and apparatus for providing a 360-degree panoramic background during a video call. A non-transitory computer-readable recording medium stores instructions that, when executed by a processor, cause the processor to perform operations for providing a background on an electronic device. The operations include separating an object video and an original background video from video data input to a first video call screen of an electronic device during a video call; generating new video data by synthesizing a panoramic video image and the object video such that the new video data includes the object video and includes the panoramic video image as a replacement background video; and displaying, on the first video call screen, the new video data such that a location of the panoramic video image of the new video data moves in response to motion information of a user.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: January 17, 2023
    Assignee: LINE Plus Corporation
    Inventors: Jinhee Yoo, Ji Seon Choi, Chihoon Ryu, Seong Ran Seo
  • Patent number: 11557309
    Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to reduce noise from harmonic noise sources. An example apparatus includes at least one memory; at least one processor to execute the computer readable instructions to at least: determine a first amplitude value of a frequency component in a frequency spectrum of an audio sample; determine a set of points in the frequency spectrum having at least one of (a) amplitude values within an amplitude threshold of the first amplitude value, (b) frequency values within a frequency threshold of the first amplitude value, or (c) phase values within a phase threshold of the first amplitude value; increment a counter when a distance between (1) a second amplitude value in the set of points and (2) the first amplitude value satisfies a distance threshold; and when the counter satisfies a counter threshold, generate a contour trace based on the set of points.
    Type: Grant
    Filed: May 24, 2021
    Date of Patent: January 17, 2023
    Assignee: The Nielsen Company (US), LLC
    Inventor: Matthew McCallum