Abstract: Disclosed are various embodiments for an external housing assembly of a sensing device externally mounted on a skewed panel of a vehicle. The external housing assembly can provide ingress protection from fluids and foreign objects. In one example, the external housing assembly includes an external housing, a cylindrical conduit, a spacer, a retention nut, and a retention ring. The external housing being configured to surround an aperture of a vehicle. The cylindrical conduit attaches to the external housing, and the sensing device having a lens that is positioned within the cylindrical conduit. The spacer is positioned adjacent to the skewed panel. The retention nut is positioned adjacent to the spacer and is attached to the cylindrical conduit. A portion of the sensing device is positioned between the retention nut and the retention ring. The retention ring is attached to the retention nut.

Abstract: Controller devices may be communicatively coupled to distributed devices in a workspace. The controller devices may be positioned in various geographic locations relative to locations of the distributed devices within the workspace. Each of the controller devices may be utilized to maintain an account of, and locally control, one or more of the distributed devices. Portal devices may utilize the controller devices to manage the distributed devices by configuring, controlling, and updating the controller devices. The control devices may be utilized to establish communication channels between the portal devices and the distributed devices to provide access for a user to the distributed devices. The communication channels may be accessible to user devices based on security credentials that are modified in real-time or near real-time.

Abstract: Systems, devices, and methods are provided for training and/or inferencing using machine-learning models. In at least one embodiment, a user selects a source media (e.g., video or audio file) and a target identity. A content embedding may be extracted from the source media, and an identity embedding may be obtained for the target identity. The content embedding of the source media and the identity embedding of the target identity may be provided to a transfer model that generates synthesized media. For example, a user may select a song that is sung by a first artist and then select a second artist as the target identity to produce a cover of the song in the voice of the second artist.

Abstract: When a client requests a data import job, a remote storage service provider provisions a shippable storage device that will be used to transfer client data from the client to the service provider for import. The service provider generates security information for the data import job, provisions the shippable storage device with the security information, and sends the shippable storage device to the client. The service provider also sends client-keys to the client, separate from the shippable storage device (e.g., via a network). The client receives the device, encrypts the client data and keys, transfers the encrypted data and keys onto the device, and ships it back to the service provider. The remote storage service provider authenticates the storage device, decrypts client-generated keys using the client-keys stored at the storage service provider, decrypts the data using the decrypted client-side generated keys, and imports the decrypted data.

Abstract: Methods and apparatus for providing persistent execution environments for computation systems including but not limited to interactive computation systems. A service is provided that extends the notion of static containers to dynamically changing execution environments into which users can install code, add files, etc. The execution environments are monitored, and changes to an execution environment are automatically persisted to environment versions(s) so that code run in the execution environment can be run later or elsewhere simply by referring to the environment. There is no explicit build step for the user. Instead, incremental changes are added to environment versions which are stored and are ready to be used to instantiate respective execution environments on other compute instances.

Abstract: Explanation jobs may be performed for computer vision tasks. A request to execute an explanation job for a computer vision machine learning model may be received. The execution job may be performed, including extracting different features from the image, determining the respective relative importance values of the different features on inferences generated by the computer vision machine learning model. The result of the explanation job, including the generated heat maps may be provided.

Abstract: A speech-processing system receives input data corresponding to one or more characteristics of speech. The system determines parameters representing the characteristics and, using the parameters, encoded values corresponding to the characteristics. A speech synthesis component of the speech-processing processes the encoded values to determine audio data including a representation of the speech and corresponding to the characteristics.

Abstract: Implementations for metering features of media conferences on the client-side are described. Initially, a participant joins a media conference. An identifier of a feature and an allotment associated with the feature is then received by the participant. The feature is used during the media conference and the allotment associated with the feature is decremented based on the use of the feature. It is then determined that an allotment refresh is needed. In response, additional allotment associated with the feature is requested and received by the participant until the maximum number of additional allotment requests or the maximum allotment is reached.

Abstract: Systems and methods for event-detection confirmation are disclosed. For example, a sensing device may generate sensor data, such as from radar, and the sensor data may be utilized to determine if a predefined event as occurred. Event-confirmation operations may then be performed, such as by utilizing acoustic-event detection techniques and/or natural language understanding techniques. When occurrence of an event is confirmed, such as to a certain confidence level, one or more actions may be taken, such as sending a notification to another device and/or establishing a communication channel with another device, such as a device associated with emergency services, family members, friends, and/or neighbors.

Abstract: Systems and methods for account association with voice-enabled devices are disclosed. For example, a voice-enabled device situated in a managed environment, such as a hotel room, may be taken by a temporary resident or guest of the environment. Upon determining that the device has been removed from the environment, a device identifier associated with the device may be dissociated from components and/or services associated with environment and/or systems related thereto, and the device identifier may be associated with a user account of the user.

Abstract: Described is a multiple-camera system and process for determining an item involved in an event. For example, when a user picks an item or places an item at an inventory location, image information for the item may be obtained and processed to identify the item involved in the event and associate that item with the user.

Abstract: Techniques for determining buggy code are described. An encoder/decoder-based (e.g., transformer-based) model approach is described. In some embodiments, a service receives request to perform transformer-based bug fixing on code, performs bug fixing inference to the code by applying a trained encoder/decoder-based model, and reports out a result of the inference, wherein the output includes an indication of a location of a potential edit to be made in the code and the potential edit in the code.

Abstract: This disclosure proposes systems and methods enabling on-device/hybrid processing of speech requests using a hub device. The hub device is capable of receiving audio data from surrounding devices and performing speech processing on the audio data to improve latency and/or provide functionality to other devices within a private network. The hub device may receive multiple requests corresponding to different utterances. If the hub device receives a second utterance while processing a first utterance, the hub device may send an error notification, process the first utterance and the second utterance sequentially, suspend processing of the first utterance to process the second utterance first, send the second utterance to another hub device or remote system, or suspend processing of the first utterance and send the first utterance to the remote system in order to process the second utterance.

Abstract: A real-time data validation system prevents problematic updates from being replicated from a primary database to a replica database. The data validation system may inject a time delay into the replication process, so that when an update in a replication stream fails a specified data validation, the data validation system will prevent the update from being applied to the replica. The replication process may be halted to take snapshot of the replica database during the halt, and resumed after the snapshot. Accordingly, if the problematic update is later confirmed to be invalid, the replica database can be rolled back to a point before the problematic update. Advantageously, the disclosed system can be used to implement a variety of data validations on top of a database replication process to protect the replica database from receiving undesired updates.

Abstract: Provided is a system for facilitating recovery of deleted computing resources in a cloud network environment. A centralized resource recovery service may communicate with a plurality of resource management services that are each configured to create, modify, or delete their respective computing resources such as storage volumes, databases, and compute instances. The resource recovery service may allow configuration of resource group policies such that deletion of grouped resources can be managed more effectively and efficiently. For example, in the event that a deleted resources matches multiple resource retention rules, the resource retention rule that encompasses multiple resource types may be used to place the deleted resource in a recoverable state so that resources of such multiple resource types can be managed according to the same resource retention.

Abstract: A system is provided for determining customized notification output based on user preferences and event information. A user may request a system to provide a notification when a future event occurs. The system may determine a custom notification/output template for the notification, where a portion of the template is determined based on a user preference. When the event occurs, the system may generate a notification using the template, where portions of the notification are determined using event information and user preferences.

Abstract: Techniques for reducing a compilation time for compiling a neural network are disclosed. A description of a neural network is received by a compiler. A plurality of operators are identified based on the description of the neural network. A plurality of subgraphs are formed, each including one or more operators. For each subgraph, a performance factor is calculated based on a compute usage and a memory usage associated with the operators included in the subgraph. The performance factor is compared to a threshold. Based on the comparison, either the subgraph is classified as a compute bound subgraph and a set of memory optimizations are suppressed or the subgraph is classified as a memory bound subgraph and a set of compute optimizations are suppressed.

Abstract: This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

Abstract: Machine learning automatic pipeline management for automated software deployment is described. An adjustment to computing capacity for a region of a multi-region computing network is identified. A service to be deployed in the region of the multi-region computing network is further identified. Configuration settings for deployment of the service in the region is generated using past deployment data for the service in other regions of the multi-region computing network. A continuous code delivery service is directed to add a stage to a software deployment pipeline for the region. The stage may be configured using the at least one configuration setting.

Abstract: A chat input identifier may receive various chat inputs based on voice or text inputs from a user. The chat input identifier may apply different filters to the chat inputs to identify one or more chat correction pairs (e.g., chat input with errors, corrected chat input) from among the plurality of chat inputs. The chat correction pairs are used to train an auto-correction model. The trained auto-correction model receives a given chat input that has one or more errors. The auto-correction model processes the given chat input to generate a corrected version of the given chat input (without the need to obtain a correction from the user). The corrected chat input is then provided to a dialog-driven application.