Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

Abstract: A method includes a hierarchical dataset that includes a root-data object and data collections nested under the root-data object. Each data collection includes one or more data objects, each data object associated with one or more other data collections. The method also includes displaying a hierarchical user interface on a screen. The hierarchical user interface includes column. The columns include data-object columns and data-collection columns, wherein the columns alternate between data-object columns and data-collection columns. Each data-object column displays a list of the one or more data objects of a respective data collection. Each data-collection column displays a list of the one or more data collections of a respective data object, the data-collection columns includes a root-data-collection column displaying a list of the one or more data collections associated with the root-data object.

Abstract: A computer-implemented method includes receiving a query specifying an operation to perform on a first table of a plurality of data blocks stored. Each data block in the first table includes a respective reference count indicating a number of tables referencing the data block. The method also includes determining that the operation specified by the query includes copying the plurality of data blocks in the first table into a second table and, in response, for each data block of the plurality of data blocks in the first table copied into the second table, incrementing, the respective reference count associated with the data block in the first table, appending, by the data processing hardware, into metadata of the second table, a reference of the corresponding data block copied into the second table.

Abstract: A method at an electronic device with a display includes: displaying a user interface having a first region and a second region; receiving, and displaying in the first region of the user interface, a live video stream of a physical environment captured by a remote video camera; displaying, in the second region, a timeline corresponding to a timespan for a first portion of a duration during which the live video stream may have been recorded; in response to receiving a user interaction to move the timespan to a second portion of the duration, transitioning the displayed timeline to a new timeline that corresponds to the timespan for the second portion, and while transitioning, displaying, in the first region, a subset of video frames representing the first and/or second portion of the duration.

Abstract: A method includes receiving a speech recognition result, and using a confidence estimation module (CEM), for each sub-word unit in a sequence of hypothesized sub-word units for the speech recognition result: obtaining a respective confidence embedding that represents a set of confidence features; generating, using a first attention mechanism, a confidence feature vector; generating, using a second attention mechanism, an acoustic context vector; and generating, as output from an output layer of the CEM, a respective confidence output score for each corresponding sub-word unit based on the confidence feature vector and the acoustic feature vector received as input by the output layer of the CEM. For each of the one or more words formed by the sequence of hypothesized sub-word units, the method also includes determining a respective word-level confidence score for the word. The method also includes determining an utterance-level confidence score by aggregating the word-level confidence scores.

Abstract: Methods and systems for calibrating a haptic system in an electronic device are provided. The calibration of the haptic system may be performed in a facility prior to a shipment to a user. The calibration may also be performed by a user prior to or after his/her use of the haptic system in the electronic device over time. A method for performing a calibration process in an electronic device includes generating a drive signal from a haptic driver in a haptic system disposed in an electronic device, transmitting the drive signal to an actuator in the haptic system, detecting a back Electromotive Force (bEMF) signal from the actuator in the haptic system, analyzing an output waveform from the bEMF signal, and adjusting a scale of the drive signal generated from the haptic driver.

Abstract: A method for integrating third-party encryption managers with cloud services includes receiving, at data processing hardware, an operation request requesting a cryptographic operation on data comprising an encryption operation or a decryption operation. When the operation is an encryption operation, the method includes transmitting a data encryption key associated with the data to a remote entity. The remote entity encrypts the data encryption key with a key encryption key and transmits the encrypted data encryption key to the data processing hardware. When the operation is a decryption operation, the method includes transmitting the encrypted data encryption key to the remote entity which causes the remote entity to decrypt the encrypted data encryption key with the key encryption key and transmit the decrypted data encryption key and transmit to the data processing hardware.

Abstract: Methods, systems, and media for demoting search results based on search query risk are provided. In some embodiments, a method for demoting search results includes: receiving a search query for a video content item; generating a plurality of search results in response to the search query; calculating a set of result goodness values; calculating a query goodness value associated with the search query based on the set of result goodness values; identifying a threshold goodness value based on the query goodness value; in response to determining that a first result goodness value of the set of result goodness values is less than the threshold goodness value, demoting a first search result of the plurality of search results, wherein the first result goodness value is associated with the first search result; and causing at least a portion of the plurality of search results to be presented based on the demotion.

Abstract: A system and method may include receiving data defining an augmented reality (AR) environment including a representation of a physical environment, identifying relationships between a plurality of scene elements in the AR environment, and obtaining a set of UI layout patterns for arranging the plurality of scene elements in the AR environment according to one or more relationships between the plurality of scene elements. The system and method may identify, for the at least one scene element, at least one relationship that corresponds to at least one UI layout pattern, generate a modified UI layout pattern for the at least one scene element using different relationships than the identified at least one relationship, and trigger display of the AR content associated with the information and the at least one scene element using the modified UI layout pattern.

Abstract: A method for detecting a movement path in a monitored environment generates a first movement path record by collecting first node information for each of a first series of nodes including at least one of a sensor ID or a device ID, and a trigger time. The method further determines a first movement path total duration time from a difference between a time of the ending node and a time of the starting node of the first series of nodes. The method further stores the first movement path record and subsequently compares a second movement path record with the first movement path record by comparing the first node information with second node information for each of a second series of nodes of the second movement path record, and the first movement path total duration time with a second movement path total duration time.

Abstract: Systems, methods, devices, and other techniques for managing a computing resource shared by a set of online entities. A system can receive a request from a first online entity to reserve capacity of the computing resource. The system determines a relative priority of the first online entity and identifies a reservation zone that corresponds to the relative priority of the first online entity. The system determines whether to satisfy the request based on comparing (i) an amount of the requested capacity of the computing resource and (ii) an amount of the portion of unused capacity of the computing resource designated by the reservation zone that online entities having relative priorities at or below the relative priority of the first online entity are permitted to reserve.

Abstract: Systems, methods, and apparatuses, including electronic devices and computer-readable storage media, for adaptively switching wireless connections between antennas of a wearable electronic device and a host electronic device. One device includes a wearable electronic device with a first and second housing, each housing including two or more antennas. The wearable electronic device is configured to establish and monitor a wireless cross-link between two antennas in different housings, or between antennas in one housing and antennas of a host electronic device. The wearable electronic device can monitor the integrity of the wireless cross-link, and establish an updated cross-link in response to the wireless cross-link not meeting a predetermined integrity threshold. The wearable electronic device can monitor a wireless cross-head link between housings of a wearable electronic device at the same time as a wireless cross-body link between the wearable electronic device and the host electronic device.

Abstract: A method for Short-Time Fourier Transform-based echo muting includes receiving a microphone signal including acoustic echo captured by a microphone and corresponding to audio content from an acoustic speaker, and receiving a reference signal including a sequence of frames representing the audio content. For each frame in a sequence of frames, the method includes processing, using an acoustic echo canceler configured to receive a respective frame as input to generate a respective output signal frame that cancels the acoustic echo from the respective frame, and determining, using a Double-talk Detector (DTD), based on the respective frame and the respective output signal frame, whether the respective frame includes a double-talk frame or an echo-only frame. For each respective frame that includes the echo-only frame, muting the respective output signal frame, and performing speech processing on the respective output signal frame for each respective frame that includes the double-talk frame.

Abstract: A method includes establishing digital communication between a first user device and a second user device using a first codec. The method also includes selecting, based on an input signal representing an estimated unfiltered available bandwidth for the digital communication satisfying a first filter selection threshold, a first filter of two or more filters, and filtering the input signal using the first filter. The method further includes determining that the filtered input signal satisfies a first channel bandwidth threshold and, in response to determining that the filtered input signal satisfies the channel bandwidth threshold, selecting a second codec different from the first codec for further digital communication between the first user device and the second user device.

Abstract: A method includes, in a computing system that runs clients on multiple interconnected compute nodes, running on the compute nodes respective virtual switches and respective virtual heads. Each client is provisioned to direct file access commands using one or more access protocols to a respective virtual head running on the compute node on which the client runs, via a respective virtual switch running on the compute node on which the client runs. The file access commands issued by the clients are executed by communicating among the virtual heads using an inter-node communication protocol that is independent of the access protocols used by the clients.

Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.

Abstract: A method of powering a controller using an intermediate device with power from an environmental system may include receiving current from a power wire from the environmental system; passing the current from the power wire to a second command wire from the controller; monitoring the current flowing between the power wire and the second command wire while the current is below a threshold indicative of an amount of current used to power the controller from the environmental system; detecting when the current flowing between the power wire and the second command wire exceeds the threshold indicating that the controller is sending a command to the environmental system to perform the function; and sending a command to environmental system using a first command wire from the environmental system after detecting that the current exceeds the threshold.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for providing search results automatically to a user of a computing device. A spoken input provided by a user to a computing device is received. The spoken input is transmitted to a computer server system that is remote from the computing device. Search result information that is responsive to the spoken input is receiving by the computing device and in response to the transmitted spoken input. An alert is provided to the user that the device will connect the user to a target of the search result information if the user does not intervene to stop the connecting of the user. The user is connected to the target of the search result information based on a determination that the user has not intervened to stop the connecting of the user.

Abstract: Method includes receiving, through a plurality of channels, audio data corresponding to a plurality of frequency ranges; determining, for each channel's frequency ranges, speech audio and/or noise energy level using a model trained by machine learning; determining a speech signal with removed noise for each channel; determining one or more statistical values associated with an energy level of a channel's speech signal with the removed noise; determining a strongest channel that has highest statistical values associated with an energy level of a speech signal; determining that the one or more statistical values associated with the energy level of the strongest channel's speech signal satisfy a threshold condition; comparing statistical values associated with an energy level of a speech signal of each channel with those of the strongest channel; and determining whether to update a gain value for a channel based on the channel's statistical values associated with the energy level.

Abstract: A system for providing advertisements with search results in response to a search query comprises a front end and an advertisement server. The front end is configured: to receive a search query; to send a first search request to a search server and sending a first advertisement request to an advertisement server, wherein the first search request includes the search query or information based on the search query, and wherein the first advertisement request includes the search query or information based on the search query and an indication that an advertisement response is not to be provided; to receive search results from the search server; and to send at least some of the search results to the advertisement server in a second advertisement request, wherein the second advertisement request includes an indication that an advertisement response is to be provided.