Abstract: Techniques and apparatuses are described that implement a signal fingerprint. In an example aspect, a fingerprint module can monitor signals distributed between a host board and peripherals during an operation performed by the host board. The fingerprint module can generate a signal fingerprint that represents characteristics of the signals that correspond to the operation. With the signal fingerprint, the fingerprint module can improve user experience by protecting the electronic device from anomalous behavior. The fingerprint module can also use the signal fingerprint to improve the user experience and improve system performance through appropriate electronic device component selection. The disclosed techniques and systems can therefore provide electronic device operation reliability, protect sensitive data, and improve electronic device performance while reducing costs and time associated with the design and testing phases of such devices.

Abstract: A method includes, while a user is wearing stereo headphones in an environment, obtaining, from a target digital assistant, a response to a query issued by the user, and obtaining spatial audio preferences of the user. Based on the spatial audio preferences of the user, the method also includes determining a spatially disposed location within a playback sound-field for the user to perceive as a sound-source of the response to the query. The method further includes rendering output audio signals characterizing the response to the query through the stereo headphones to produce the playback sound-field. Here, the user perceives the response to the query as emanating from the sound-source at the spatially disposed location within the playback sound-field.

Abstract: Aspects of the disclosure are directed to early filtering of candidate rows for a join operator of a query statement before the join operator is evaluated to generate a result set. Early filtering, e.g., before execution of the join operator, reduces the number of candidate rows fetched from a database during a join operator, which can improve the rate at which queries including join operators are executed by a DBMS for the database. One or more Bloom filters or other probabilistic data structures can be produced and consumed according to different join conditions, allowing for early pruning of unqualified rows during a database scan operation.

Abstract: Techniques and apparatuses are described for video frame codec architectures. A frame decompressor decompresses compressed frames to produce decompressed frames. A frame decompressor controller arbitrates shared access to the frame decompressor. Multiple cores of an SoC request to receive a decompressed frame from the frame decompressor via the frame decompressor controller. The frame decompressor controller can implement a request queue and can order the servicing of requests based on priority of the requests or requesting cores. The frame decompressor controller can also establish a time-sharing protocol for access by the multiple cores. In some implementations, a video decoder is logically integrated with the frame decompressor and stores portions of a decompressed frame in a video buffer, and a display controller retrieves the portions for display using a synchronization mechanism. In analogous manners, a frame compressor controller can arbitrate shared access to a frame compressor for the multiple cores.

Abstract: The present technology proposes techniques for ensuring globally consistent transactions. This technology may allow distributed systems to ensure the causal order of read and write transactions across different partitions of a distributed database. By assigning causally generated timestamps to the transactions based on one or more globally coherent time services, the timestamps can be used to preserve and represent the causal order of the transactions in the distributed system. In this regard, certain transactions may wait for a period of time after choosing a timestamp in order to delay the start of any second transaction that might depend on it. The wait may ensure that the effects of the first transaction are not made visible until its timestamp is guaranteed to be in the past. This may ensure that a consistent snapshot of the distributed database can be determined for any past timestamp.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly performing text detection and layout analysis. In one aspect, a method comprises processing the image and a set of object queries to generate an encoded representation of the image and an encoded representation of the set of object queries; processing the encoded representation of the image and the encoded representation of the set of object queries to generate a set of text detection masks; processing the encoded representation of the set of object queries to generate layout relevance measures; processing the encoded representation of the set of object queries to generate textness scores for the text detection masks; generating a text detection output that defines respective areas of the image that include text items; and generating a layout analysis output that defines clusters of respective areas of the image identified by the text detection masks.

Abstract: A method includes determining that a user device is located within a specified geographical region, and determining that the user device has an active subscription with a terrestrial network operator operating a terrestrial network within the geographical region, the terrestrial network associated with a primary profile stored on a subscriber identity module of the user device. The method also includes, in response to determining that the user device is located within the geographical region and that the user device has an active subscription with the terrestrial network operator, receiving, from the terrestrial network operator, a secondary profile attached to the active subscription and associated with a non-terrestrial communication network. The method further includes storing the secondary profile on an embedded subscriber identity module on the user device, and communicating via the non-terrestrial communication network using the secondary profile.

Abstract: A method for anomaly detection includes receiving an anomaly detection query from a user. The anomaly detection query requests data processing hardware determine one or more anomalies in a dataset including a plurality of examples. Each example in the plurality of examples is associated with one or more features. The method includes training a model using the dataset. The trained model is configured to use a local outlier factor (LOF) algorithm. For each respective example of the plurality of examples in the dataset, the method includes determining, using the trained model, a respective local deviation score based on the one or more features. The method includes determining that the respective local deviation score satisfies a deviation score threshold and, based on the location deviation score satisfying the threshold, determining that the respective example is anomalous. The method includes reporting the respective anomalous example to the user.

Abstract: Methods and devices are provided where a wearable device may receive sensor data and activate a recipe building mode of the wearable device when the sensor data satisfies a commencement condition. An image sensor of the wearable device may capture images of a physical environment. A recognition engine of the wearable device may identify ingredients detected in the images, determine an amount of the ingredients, identify utensils detected in the images, track actions of a user based on the images, and determine the name of a recipe, in response to terminating the capture of the images. The wearable device may store the recipe, the recipe including the name of the recipe, the ingredients, the amount of ingredients, the utensils, the actions of the user, and the one or more images. The recipe may be annotated with captions and output on a display of the wearable device.

Abstract: A method includes receiving user queries directed toward a cloud-based assistant service. For each received user query directed toward the cloud-based assistant service, the method also includes extracting one or more attributes from the user query and logging the user query into one or more of a plurality of category buckets based on the one or more attributes extracted from the user query. The method also includes determining when at least one of the plurality of category buckets includes a threshold number of the user queries logged into the at least one category bucket, and when the at least one of the plurality of category buckets includes the threshold number of the user queries, generating a distilled model of the cloud-based assistant service. The distilled model of the cloud-based assistant service is configured to execute on one or more target client devices.

Abstract: Methods and systems for time marking of media items at a platform using machine-learning are provided herein. An indication of a identified media item is provided as input to a machine-learning model and one or more outputs of the machine-learning model is obtained. The one or more obtained outputs comprise time marks identifying each of the plurality of content segments of the media item. Each of the plurality of content segments is associated with a segment start indicator for a timeline of the media item. A resulting duration is determined of a combination of the plurality of content segments for which the time marks were obtained from the one or more of outputs of the machine-learning model. Responsive to determining that the resulting duration is less than the duration of the media item, one or more further inputs is provided to the machine learning model.

Abstract: This document describes systems and techniques for improving the integrity and protecting the security of information in content selection and distribution. In one aspect, a method includes receiving, by a first server of a secure multi-party computation (MPC) system from an application on a user device, a request for a digital component. The request is parsed into distinct sub-requests. Each sub-request is transmitted to a different server. A set of candidate selection values is received from a separate server. The first server performs, in collaboration with one or more second servers of the MPC system, a selection process to generate a selection result for a winning digital component, including merging, the first set of candidate selection values and a set of cached selection values to create a final set of candidate selection values and sorting the final set according to the values of the candidate selection values.

Abstract: Various arrangements for enhancing audio are detailed herein. An audio stream and a second audio stream can be received. From these audio streams, a first audio source and a second audio source are extracted. A conversation between the first audio source and a third audio source that occurs within the audio streams is identified. An updated audio stream is generated that enhances the first audio source and diminishes the second audio source extracted from the audio stream and the second audio stream.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing storage devices. In some implementations, a memory controller receives a logical write request over a logical interface that the memory controller provides for accessing a non-volatile storage device. The logical write request indicates a logical address at which to write data to the non-volatile storage device. In response to receiving the logical write request, the memory controller sends a write request event to a host system. The memory controller receives a physical write command from the host system over a physical interface that the memory controller provides for accessing the non-volatile storage device. In response to receiving the physical write command, the memory controller stores the data in the non-volatile storage device according to the physical write command.

Abstract: The various implementations described herein include methods, devices, and systems for monitoring activity in a home environment. In one aspect, a method performed at a voice-assistant device includes: detecting a sound; obtaining a determination as to whether the sound meets one or more monitoring criteria; and in accordance with a determination that the sound meets the one or more monitoring criteria, generating a notification.

Abstract: Apparatus and methods related to image processing are provided. A computing device can determine a first image area of an image, such as an image captured by a camera. The computing device can determine a warping mesh for the image with a first portion of the warping mesh associated with the first image area. The computing device can determine a cost function for the warping mesh by: determining first costs associated with the first portion of the warping mesh that include costs associated with face-related transformations of the first image area to correct geometric distortions. The computing device can determine an optimized mesh based on optimizing the cost function. The computing device can modify the first image area based on the optimized mesh.

Abstract: A system and method for conducting a parameter update event including one or more processors for transmitting first parameter settings to a program used by multiple users, such as a mobile device application at a plurality of mobile devices, receiving performance information indicating performance of the program after the first parameter setting, the performance information for each user being separately identifiable, and for each individual user of the plurality of users, determining a parameter setting update based at least in part on the performance information of the individual user and transmitting the parameter setting update to the program.

Abstract: A method for training a model includes obtaining a plurality of training samples. Each respective training sample of the plurality of training samples includes a respective speech utterance and a respective textual utterance representing a transcription of the respective speech utterance. The method includes training, using quantization aware training with native integer operations, an automatic speech recognition (ASR) model on the plurality of training samples. The method also includes quantizing the trained ASR model to an integer target fixed-bit width. The quantized trained ASR model includes a plurality of weights. Each weight of the plurality of weights includes an integer with the target fixed-bit width. The method includes providing the quantized trained ASR model to a user device.

Abstract: The technology generally relates to systems and methods for performing in-field testing of processing cores within a system-on-chip (SoC), so as to identify faults, including those associated with silent data corruption. For example, an SoC may contain operational cores and spare cores. An operational core may be selected for testing while a spare core is used to replace the tested core. In addition, a spare core may be used to replace an operational core that has been determined to be corrupted.