Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process.

Abstract: A computer-implemented method for executing a default action on a touchscreen device is provided. The method includes receiving a touch input from a user on a touchscreen device and determining a context associated with the touch input. The context is associated with one or more actions including a default action. The method also includes determining that the received touch input comprises a default gesture, and performing the default action associated with the determined context. The default gesture may be a two-finger double-tap gesture. Systems and machine-readable media are also provided.

Abstract: A method includes receiving a build request containing build step instructions from a user. The build step instructions specify a usage of containers within memory hardware for building an output container. The containers include at least one private container having private contents and/or at least one public container having public contents. The method also includes authenticating the user initiating the build request and determining whether the user is authorized to access the private containers. When the user is authenticated and authorized to access the private containers, the method includes obtaining the containers specified by the build step instructions from the memory hardware, executing the build step instructions to build the output container while using the received containers, and outputting the built output container.

Abstract: Methods, systems, and apparatus, including a method for updating user consent in a verifiable manner. In some aspects, a method includes receiving, from a client device, a request including an attestation token. The attestation token includes a set of data that includes at least a user identifier that uniquely identifies a user of the client device, a token creation time that indicates a time at which the attestation token was created, user consent data specifying whether one or more entities that receive the attestation token are eligible to use data of the user, an action to be performed in response to the request. The attestation token also includes a digital signature of at least a portion of the set of data, including at least the user identifier and the token creation time. An integrity of the request is verified using the attestation token.

Abstract: A method includes obtaining a batch of training samples. For each particular training sample in the batch of training samples, the method includes generating, using a data value estimator model and the particular training sample, a corresponding predicted value of the particular training sample when used to train a machine learning model. The method includes selecting, based on the corresponding predicted values, a subset of the batch of training samples. For each particular training sample in the subset of the batch of training samples, the method includes determining, using the machine learning model and the particular training sample, a corresponding prediction performance measurement. The method includes adjusting one or more estimator parameter values of the data value estimator model based on the corresponding prediction performance measurements.

Abstract: A method for a contextual assistant to use mouse pointing or touch cues includes receiving audio data corresponding to a query spoken by a user, receiving, in a graphical user interface displayed on a screen, a user input indication indicating a spatial input applied at a first location on the screen, and processing the audio data to determine a transcription of the query. The method also includes performing query interpretation on the transcription to determine that the query is referring to an object displayed on the screen without uniquely identifying the object, and requesting information about the object. The method further includes disambiguating, using the user input indication indicating the spatial input applied at the first location on the screen, the query to uniquely identify the object that the query is referring to, obtaining the information about the object requested by the query, and providing a response to the query.

Abstract: A method of resizing a block storage volume for a virtual machine includes executing the virtual machine and attaching a virtual storage device to the virtual machine. The virtual storage device exposes the block storage volume on memory hardware to the virtual machine. The block storage volume includes a first storage capacity. The method also includes mounting the block storage volume to the virtual machine and resizing the block storage volume while the virtual machine continues to execute. The block storage volume is resized without attaching an additional virtual storage device to the virtual machine or mounting an additional block storage volume to the virtual machine.

Abstract: A Wi-Fi chip is configured to operate in a power saving Wi-Fi mode in which the Wi-Fi chip repeatedly checks, at a first time interval, periodic DTIM beacons transmitted at a second time interval by a wireless access point of a Wi-Fi network, wherein the first time interval is longer than the second time interval. Upon receiving a standby message, the Wi-Fi chip, during a predefined time duration, operates in a standby mode in which the Wi-Fi chip checks at a third time interval periodic DTIM beacons transmitted by the wireless access point, wherein the third time interval is shorter than the first time interval.

Abstract: An automated speech recognition (ASR) model includes a first encoder, a first encoder, a second encoder, and a second decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The first decoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a first probability distribution over possible speech recognition hypotheses. The second encoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a second higher order feature representation for a corresponding first higher order feature frame. The second decoder receives, as input, the second higher order feature representation generated by the second encoder, and generates a second probability distribution over possible speech recognition hypotheses.

Abstract: A method includes obtaining a set of unlabeled training samples. For each training sample in the set of unlabeled training samples generating, the method includes using a machine learning model and the training sample, a corresponding first prediction, generating, using the machine learning model and a modified unlabeled training sample, a second prediction, the modified unlabeled training sample based on the training sample, and determining a difference between the first prediction and the second prediction. The method includes selecting, based on the differences, a subset of the set of unlabeled training samples. For each training sample in the subset of the set of unlabeled training samples, the method includes obtaining a ground truth label for the training sample, and generating a corresponding labeled training sample based on the training sample paired with the ground truth label. The method includes training the machine learning model using the corresponding labeled training samples.

Abstract: A method includes, while a user device is using a first presentation mode to present content to a user, obtaining a current state of the user of the user device. The method also includes, based on the current state of the user, providing, as output from a user interface of the user device, a user-selectable option that when selected causes the user device to use a second presentation mode to present the content to the user. The method further includes, in response to receiving a user input indication indicating selection of the user-selectable option, initiating presentation of the content using the second presentation mode.

Abstract: This disclosure relates to deep trench capacitors embedded in a package substrate on which an integrated circuit is mounted. In some aspects, a chip package includes an integrated circuit die that has a power distribution circuit for one or more circuits of the integrated circuit. The chip package also includes a substrate different from the integrated circuit and having a first surface on which the integrated circuit die is mounted and a second surface opposite the first surface. The substrate includes one or more cavities formed in at least one of the first surface or the second surface. The chip package also includes one or more deep trench capacitors disposed in at least one of the one or more cavities. Each deep trench capacitor is connected to the power distribution circuit by conductors.

Abstract: Aspects of the disclosure are directed to generating a hybrid query execution plan for executing queries on database systems implementing a columnar cache. A hybrid query execution plan combines a query execution plan for querying and retrieving data from a columnar cache and a base table. A columnar cache stores cached data in column-major format, which is logically represented by the database management system in row-major format. A database management system as described herein can scan valid blocks of column data according to a column scan operation. The system can identify invalidated blocks and execute a different sub-execution plan of the hybrid query execution plan to scan corresponding rows in tables corresponding to the location of data for the invalidated blocks.

Abstract: Techniques for performing an emissions demand response event are described. In an example, a cloud-based HVAC control server system receives an emissions rate forecast for a predefined future time period. Using the emissions rate forecast, a plurality of emissions differential values are created for a plurality of points in time during the predefined future time period. The emissions differential values represent a change in predicted emissions over time. Based on the plurality of emissions differential values and a predefined maximum number of emissions demand response events, an emissions demand response event is generated during the predefined future time period. The cloud-based HVAC control server system then causes a thermostat to control an HVAC system in accordance with the generated emissions demand response event.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for gamma lookup table compression. In one aspect, a method includes obtaining a gamma value for a pixel of an image to be shown on a display, determining a base gamma value based on a base lookup table that corresponds to a base display condition, determining a delta gamma value based on a delta lookup table that corresponds to a current display condition for the pixel, determining a remapped gamma value for the pixel based on a combination of the base gamma value and the delta gamma value, and providing the remapped gamma value to be shown on the display.

Abstract: The present disclosure provides a system for intelligently sampling information, such as location, activities, etc. on device. Sampling and uploading of background context is optimized using machine learning, such that battery usage is reduced, and quality of metrics based on the reported information is maintained or improved. A policy is generated based on the machine learning, the policy dictating how scanning and upload rates should change in response to conditions on the device.

Abstract: Systems and techniques are provided for automation and recommendation based on device control protocols. HDMI-CEC device control data may be received from a connected electronic device that may be connected to an electronic display device. The HDMI-CEC device control data may be based on a HDMI-CEC device control signal from the electronic display device. The system may generate a control signal for a device. The control signal may be sent to the device for implementation.

Abstract: Method and device for image frame selection are provided. A computing device can receive, from an image capture device, a plurality of frames including a capture frame. The computing device can determine a computer-selected frame of the plurality of frames. The computing device can receive, by way of a user interface, a selection of an option to view the capture frame. The computing device can, responsive to receiving the selection, provide, by way of the user interface, an animation between the capture frame and the computer-selected frame. The animation includes an interpolation of one or more frames captured between the capture frame and the computer-selected frame.

Abstract: A distributed resource model is described that maintains traits of resources in a distributed computing system. The traits include properties, commands, and events that, along with protocols operating in the distributed computing system, provide real-time access to the traits of resources in the distributed computing system, as well as real-time command of controls for the resources. Controllers manage and publish the traits of resources and provide various types of functionality, such as arbitration, complexity management, fan-out of capabilities, coordination, adaptation, and resource proxying.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.