Abstract: A method for generating an individualized audio output response for a headset based on images of a user's ear. An image of a portion of a user's head including at least the user's ear is received, the user in the image wearing a headset including a plurality of visual markers. One or more features describing the user's ear are identified based at least in part on a position of one of the plurality of visual markers relative to the user's ear that are used to disambiguate orientation and/or scale of the features in the image. The one or more features are input to a model, and the model is configured to determine an audio output response of the user based on the extracted one or more features. An individualized audio output response is generated for the user based on the audio output response, the individualized audio output response configured to adjust one or more acoustic parameters of audio content provided to the user by the headset.

Abstract: In one embodiment, a method includes accessing foreground visual data that comprises a set of coordinate points that correspond to a plurality of surface points of a person in an environment; generating a bounding box for the set of coordinate points, wherein the bounding box comprises every coordinate point in the set of coordinate points; providing instructions to collect background visual data for an area in the environment that is outside of the bounding box; and providing the foreground visual data and the background visual data to an intelligent director associated with the computing device.

Abstract: A computer-implemented method for displaying augmented-reality objects may include capturing, by an augmented-reality system, an image of a user's hand. The method may also include applying a machine learning model to the image to identify a set of key points and determine a gesture of the hand based on the key points. In addition, the method may include identifying a targeted area of the image containing a portion of a finger based on the key points and the gesture and, subsequently, detecting a pair of edge contours of the finger by performing a computer vision method on the targeted area. Furthermore, the method may include extrapolating a location to place an augmented-reality object on the finger. Finally, the method may include displaying, by the augmented-reality system, the augmented-reality object at the location on the finger by tracking the key points. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a computing system may collect data samples associated with a geographic area of interest covered by a communication network. The system may aggregate the data samples into data points. The system may split the aggregated data points into two sets of data points using a first threshold of a first network metric. The system may determine a trend of a second network metric over the first network metric based on regression on the two sets of data points. The system may determine a predicted gain of the second network metric for a network enhancement operation based on the trend of the second network metric and a reference value of the first network metric. The system may generate network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric.

Abstract: In one embodiment, a method includes, by one or more computing systems, receiving, from a client system associated with a user, a request for a summary of user communications from a content source, accessing a plurality of user communications from the content source, identifying a plurality of segments associated with the plurality of user communications, wherein the plurality of segments is associated with a plurality of topics, respectively, calculating, for each segment of the plurality of segments, a user interest score for the segment, selecting one or more of the segments for summarization based on their user interest scores, generating one or more personalized summaries of the one or more selected segments, wherein the personalization of the summary is based on the user profile of the user and sending, to the client system, instructions to present the personalized summaries to the user responsive to the request.

Abstract: The disclosed computer-implemented method for performing directional beamforming according to an anticipated position may include accessing environment data indicating a sound source within an environment. The device may include various audio hardware components configured to generate steerable audio beams. The method may also include identifying the location of the sound source within the environment based on the accessed environment data, and then steering the audio beams of the device to the identified location of the sound source within the environment. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A system reduces power consumption by optimizing a selection of acoustic sensors of a sensor array based on environmental parameters of a local area. The system includes the sensor array including the acoustic sensors configured to detect sound in a local area, and processing circuitry. The processing circuitry is configured to: determine an environmental parameter of the local area; determine a performance metric for the sensor array; determine a selection of a subset of acoustic sensors from the acoustic sensors of the sensor array that satisfies the performance metric based on the environmental parameter of the local area; and process audio data from the subset of the acoustic sensors of the sensor array.

Abstract: A method includes generating, by an illumination source, an optical beam and coupling the optical beam into an acousto-optic device. The acousto-optic device generates structured light from the coupled optical beam by diffracting the optical beam into at least two interfering optical beams. The interfering optical beams are then used to illuminate a surface of an eye of a user of a display for use in eye-tracking.

Abstract: In some examples, a method comprises: obtaining, by an artificial reality system including a head mounted display (HMD), image data via an image capture device, the HMD configured to output artificial reality content; detecting, by the artificial reality system, a physical peripheral device from the image data; detecting, by the artificial reality system, a pose of the peripheral device; generating, by the artificial reality system, based on the pose of the peripheral device, a virtual pointer along at least a portion of a line between the peripheral device and a virtual surface, the virtual pointer pointing at a location of the virtual surface; performing, by the artificial reality system, one or more actions based on the location of the virtual surface; and rendering, by the artificial reality system, the virtual pointer and the virtual surface for display at the HMD.

Abstract: In one embodiment, a method by a stage device includes receiving from a client device a first randomized client address to be used during a pairing session; sending to the client device a first randomized stage address to be used during the pairing session; communicating with the client device using the first randomized client address and the first randomized stage address to establish at least one common randomization parameter; periodically generating, based on the at least one common randomization parameter, a second randomized client address and a second randomized stage address; and communicating with the client device in a paired communication session using the second randomized client address and the second randomized stage address.

Abstract: In one embodiment, a method includes, by one or more computing devices, receiving, from a client system of a user, a request for event recommendations for the user; accessing information indicating a geographic location associated with the user; accessing a geographic map comprising multiple map tiles, each map tile defining a geographic area within the map; identifying a first map tile of the multiple map tiles associated with the user based on the geographic location associated with the user; and determining a social tile associated with the first map tile, wherein the social tile comprises the first map tile and one or more second map tiles of the multiple map tiles, wherein the first map tile and the one or more second map tiles are clustered into the social tile based on one or more items of prior attendee information corresponding to one or more prior events.

Abstract: The disclosed computer-implemented method may include (1) receiving a first 2D frame depicting an evolving 3D scene and elements in the evolving 3D scene, (2) receiving a second 2D frame depicting the evolving 3D scene and the elements, (3) deriving 2D motion vectors from the first 2D frame and the second 2D frame that each include an estimated offset from coordinates of an element in the first 2D frame to coordinates of the element in the second 2D frame, (4) receiving depth information for the evolving 3D scene, (5) using the 2D motion vectors and the depth information to extrapolate a synthetic 2D frame, and (6) displaying the synthetic 2D frame to a user. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An audio system includes a transducer assembly, an optical sensing pathway, a laser, a detector assembly, and a controller. The transducer assembly is coupled to a user's ear and produces an acoustic pressure wave based on an audio instruction. The optical sensing pathway moves, at least in part, with a detected acoustic pressure wave. The laser emits light that is separated into a reference beam and a sensing beam that is coupled into the optical sensing pathway. The detected acoustic pressure wave interacts with the sensing beam to alter its optical path length. The detector assembly detects the reference and sensing beams from the optical sensing pathway, and measures the detected acoustic pressure wave based on changes in optical path length between the reference beam and the sensing beam. The controller adjusts the audio instruction based on the measurement of the detected acoustic pressure wave.

Abstract: In one embodiment, a computing system may receive, from a number of artificial reality devices each corresponding to a respective user, data generated by different artificial reality applications executing on the number of artificial reality devices. The data includes contextual information associated with experiences of the number of users in different artificial reality environments generated by the different artificial reality applications. The computing system may identify a target user of a number of users, and then select a portion of the received data based on information associated with the target user. The selected portion of the received data is associated with one of the different artificial reality applications. The computing system may then generate output data for the target user based on the selected portion of the received data, and further provide the output data to an artificial reality device corresponding to the target user.

Abstract: In one embodiment, a method includes receiving a user input from a client system associated with a user, generating a plurality of candidate responses by a natural-language generation module in response to the user input, determining a quality-indication by a filtering module for each candidate response of the plurality of candidate responses based on one or more classification models and one or more classification rules, wherein the classification models and classification rules are based on one or more acceptance-criteria, selecting one or more candidate responses from the plurality of candidate responses based on their respective quality-indications, ranking the selected candidate responses based on one or more ranking-criteria, and sending instructions for presenting a top-ranked candidate response to the user to the client system associated with the user responsive to receiving the user input.

Abstract: An email-like user interface displays a list of user logs determined based on user-specified list criteria to user logs received in a natural language (NL) training environment. The list comprise a subset of the received user logs in order to minimize the number of actions required to configure and train the NL configuration system in a semi-supervised manner, thereby improving the quality and accuracy of NL configuration system. To determine a list of user logs relevant for training the user logs can be filtered, sorted, grouped and searched within the email-like user interface. A training interface to a network of instances that comprises a plurality of NL configuration systems leverages a crowd-sourcing community of developers in order to efficiently create a customizable NL configuration system.

Abstract: A touch sensing assembly includes a touch sensing layer that is configured to couple to an interface. The interface is configured to receive contact with skin of a user on a first surface. A first touch sensing layer is coupled to interface. The first touch sensing layer includes a plurality of touch sensors and a plurality of electrodes. The touch sensors are of a first touch sensing type, configured to detect proximity of the user's skin to the interface. The electrodes provide a plurality of electrical signals corresponding to the proximity of the user's skin to the interface.

Abstract: The disclosed computer-implemented method may include (1) establishing a communication channel to indirectly convey a conversation, (2) receiving, via the communication channel, a portion of the conversation, (3) presenting the portion of the conversation to a user, (4) receiving, via the communication channel, an additional portion of the conversation, (5) detecting an additional communication channel capable of conveying the conversation, (6) determining a human-perceivable difference between how the conversation has been conveyed via the communication channel and how the conversation will be conveyed via the additional communication channel, and (7) compensating for the human-perceivable difference when presenting the additional portion of the conversation to the user in order to smoothly transition the conversation from the communication channel to the additional communication channel. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A virtual reality system including a garment worn by a user, such as a glove, includes a jamming that jams movement of a portion of the user's body by increasing a rigidity of certain portions of the garment or by preventing a certain portion of the garment from expanding past a certain length. This allows the garment to simulate the physical sensation that occurs when the user touches an object. For example, to simulate the sensation of holding a coffee mug, the jamming mechanism prevents the user's fingers from curling after the user's fingers have reached a position equivalent to making physical contact with the coffee mug.