Abstract: A program is executed using a call stack and shadow stack. The call stack includes frames having respective return addresses. The frames may also store variables and/or parameters. The shadow stack stores duplicates of the return addresses in the call stack. The call stack and the shadow stack are maintained by, (i) each time a function is called, adding a corresponding stack frame to the call stack and adding a corresponding return address to the shadow stack, and (ii) each time a function is exited, removing a corresponding frame from the call stack and removing a corresponding return address from the shadow stack. A backtrace of the program's current call chain is generated by accessing the return addresses in the shadow stack. The outputted backtrace includes the return addresses from the shadow stack and/or information about the traced functions that is derived from the shadow stack's return addresses.

Abstract: A method of operating a device, which includes providing a user interface with a display artifact; in response to an indication a user selected to copy the display artifact, storing multiple levels of detail of the display artifact; allowing the user to paste a selected level of detail by steps of: in response to an indication a user selected an input field and a paste command, displaying a plurality of paste options for pasting the display artifact into the input field, wherein the plurality of paste options each have a unique level of detail for representing the display artifact; allowing the user to select from the plurality of paste options; and in response to an indication a user selected a paste option from the plurality of paste options, pasting the display artifact with a level of detail associated with the selected paste option into the input filed.

Abstract: Some embodiments support embedding of a notebooks software component in a surrounding host application, thereby promoting consistency of notebook user interfaces and user experiences between different kinds of applications. For instance, the notebook access added to an integrated development environment (IDE) may be aesthetically consistent with the notebook access added to a business analytics tool from the same vendor as the IDE. Departures from the aesthetic are still supported, e.g., a notebook access provided in a video gaming environment to teach gamers programming skills may have the same aesthetic as the simulated world of the video game, rather than an IDE aesthetic or an enterprise software aesthetic. Direct integration or proxied integration architectures may be used. Efficiencies may be gained by distinguishing between notebook viewing, editing, and executing operations, and providing more computationally expensive resources only as needed for the notebook access being performed.

Abstract: Systems and methods for data anomaly detection include recommending one or more algorithms from a set of algorithms to process received time series data, wherein the one or more algorithms are recommended based at least in part on a type of workload for processing the received time series data. Assisted parameter tuning is provided for a detected anomaly alert and calibration, and the received time series data is processed based on a user selected algorithm that is parameter tuned.

Abstract: Systems and methods are provided for assigning and associating resources in a cloud computing environment. Virtual machines in the cloud computing environment can be assigned or associated with pools corresponding to users as dedicated, standby, or preemptible machines. The various states provide users with the ability to reserve a desired level of resources while also allowing the operator of the cloud computing environment to increase resource utilization.

Abstract: The present disclosure provides a technical solution of multi-modal chatting, which may provide response to user query by using multi-modal response in the interaction between chatbot and human beings, so that the expressing ways and the expressed content by the chatbot could be richer by using such response in a multi-modal way.

Abstract: A virtual network comprising virtual machines executing at a computing environment remote from the virtualized computing service provider is implemented. A control plane management functions is configured to provide and implement the virtual machines of the virtual network and executed at the virtualized computing service provider. Data plane management functions are configured to manage data traffic to and from the virtual machines of the virtual network and executed at the remote computing environment. A secure network connection between the virtualized computing service provider and the remote computing environment is established. The control plane management functions cause instantiation of the virtual machines of the virtual network at the remote computing environment. Using the control plane management functions executing at the virtualized computing service provider, operation of the virtual machines of the virtual network is managed.

Abstract: Method and apparatus for generating speech through multilingual neural text-to-speech (TTS) synthesis are provided in the present disclosure. A text input in at least a first language may be received. Speaker latent space information of a target speaker may be provided through a speaker encoder. Language latent space information of a second language may be provided through a language encoder. At least one acoustic feature may be generated, through an acoustic feature predictor, based on the text input, the speaker latent space information and the language latent space information of the second language. A speech waveform corresponding to the text input may be generated, through a neural vocoder, based on the at least one acoustic feature.

Abstract: A data processing system is implemented for detecting changes to infrastructure components, and extracting metadata associated with the changes. The data processing system also implements grouping the changes based on the metadata, ranking the groups of changes based on past incidents of service outages, and displaying the ranked groups of changes to a user.

Abstract: Solutions for adapting machine learning (ML) models to neural networks (NNs) include receiving an ML pipeline comprising a plurality of operators; determining operator dependencies within the ML pipeline; determining recognized operators; for each of at least two recognized operators, selecting a corresponding NN module from a translation dictionary; and wiring the selected NN modules in accordance with the operator dependencies to generate a translated NN. Some examples determine a starting operator for translation, which is the earliest recognized operator having parameters. Some examples connect inputs of the translated NN to upstream operators of the ML pipeline that had not been translated. Some examples further tune the translated NN using backpropagation. Some examples determine whether an operator is trainable or non-trainable and flag related parameters accordingly for later training.

Abstract: Methods for synchronizing a source document repository with a target document repository include monitoring documents of the source document repository to detect changes to the documents. A last processed time is stored in association each changed document that indicates a time when the document was last processed. A transaction item is added to a synchronization queue each time a document is changed, and a queue time is stored in association with each of the transaction items that indicates when the transaction item was added to the queue. The transaction items are processed by comparing the queue time of the transaction item with the last processed time of the document pertaining to the transaction item. If the queue time is earlier than the last processed time, the transaction item is ignored.

Abstract: A computing device, including memory, an accelerator device, and a processor. The processor may generate a plurality of data packs that each indicate an update to a variable of one or more variables of a combinatorial cost function. The processor may transmit the plurality of data packs to the accelerator device. The accelerator device may, for each data pack, retrieve a variable value of the variable indicated by the data pack and generate an updated variable value. The accelerator device may generate an updated cost function value based on the updated variable value. The accelerator device may be further configured to determine a transition probability using a Monte Carlo algorithm and may store the updated variable value and the updated cost function value with the transition probability. The accelerator device may output a final updated cost function value to the processor.

Abstract: Techniques of automated interoperation tracking in computing systems are disclosed herein. One example technique includes tokenizing a first event log from a first software component and a second event log from the second software component by calculating frequencies of appearance corresponding to strings in the first and second event logs and selecting, as tokens, a first subset of the strings in the first event log and a second subset of the strings in the second event log individually having calculated frequencies of appearance above a preset frequency threshold. The example technique can also include generating an overall event log for a task executed by both the first and second software components by matching one of the strings in the first subset to another of the strings in the second subset.

Abstract: One example provides a computing device configured to capture, via the camera, first image data imaging a first physical world location, create a first spatial representation of the first physical world location based on the first image data, receive a user input defining a pose of a first virtual spatial anchor point relative to a feature imaged in the first image data, track user movement to a second physical world location, capture second image data imaging the second physical world location, receive a user input defining a pose of a second virtual spatial anchor point relative to a feature imaged in the second image data, and send, to a remote computing device, data representing the first spatial representation, the pose of first spatial anchor point, the second spatial representation, the pose of second spatial anchor point, and a positional relationship between first and second spatial anchor points.

Abstract: A synchronization adapter is coupled to the application that does not support synchronization and generates the necessary synchronization metadata for all data in the application that is to be synchronized. The synchronization adapter then combines the metadata to the actual data to be synchronized to form a synchronization feed. The synchronization feed is stored in an internal cache (or data store) which is internal to the application, or an external cache (or data store), which is external to the application, or it can be stored in both caches. The synchronization adapter also intermittently determines whether the application data has changed, thus warranting a change in its metadata, or whether a synchronization operation is warranted to synchronization operation is warranted to synchronize the data with data in another application. In either case, the synchronization adapter makes the changes to the data, or performs a synchronization operation.

Abstract: A control system controls tenant services to various tenants by obtaining tenant attributes for each tenant, with respect to a particular workload. A model is generated that models tenant usage performance for a set of best performing tenants. The model is then applied to a remainder of the tenants to obtain a metric indicative of a likely tenant capacity for incremental usage of the workload. The control system controls the services provided to the tenant based upon the likelihood of adoption metric.

Abstract: Computer-implemented systems and methods for rendering a visual effect on a graphical element, including: generating an initial visual effect based on the graphical element; computing a mask shape based on the graphical element; generating a mask based on the mask shape from the graphical element; masking the initial visual effect based on the mask to generate a masked visual effect; and combining the masked visual effect with the graphical element into a combined graphical element and visual effect.

Abstract: The present disclosure provides method and apparatus for generating a response in a human-machine conversation. A first sound input may be received in the conversation. A first audio attribute may be extracted from the first sound input, wherein the first audio attribute indicates a first condition of a user. A second sound input may be received in the conversation. A second audio attribute may be extracted from the second sound input, wherein the second audio attribute indicates a second condition of a user. A difference between the second audio attribute and the first audio attribute is determined, wherein the difference indicates a condition change of the user from the first condition to the second condition. A response to the second sound input is generated based at least on the condition change.

Abstract: Systems and methods are provided for automatically generating a fault-enabled software development kit (SDK) to test an application. The generating includes determining one or more faults based on codes associated with the SDK and a frequency of occurrences of faults while executing the SDK. A fault injector automatically injects the determined faults in select layers of code in the SDK and generates fault configuration data associated with the automatically injected faults in the SDK. The fault configuration data describes faults that have been injected in the fault-enabled SDK to test an application. The fault-enabled SDK tests the application without needs for modifying the application code for testing purposes. The fault-enabled SDK further provides types of faults that may be common in using the SDK without requiring application developers to have detailed understanding of internals of the SDK to test the application with simulated faults.

Abstract: A computer implemented method includes accessing a first status of a first battery pack interface coupled to a load via a first load switch and accessing a second status of a second battery pack interface coupled to the load via a second load switch. The first status and the second status are compared and the first and second load switches are controlled based on the comparing to balance remaining capacities of the first and second battery packs.

Abstract: Techniques for artificially generating commentary for online content including news items. In an aspect, a personification engine incorporates a machine learning model trained using corpus elements comprising an item of online content and relevant commentary. The personification engine is configured to generate relevant commentary when provided with an item of online content such as a news item. In a further aspect, a chatbot engine incorporates a model similarly trained using corpus element comprising a comment and a relevant response. The chatbot engine is configured to generate relevant responses to user comments in the context of a forum or comments section related to the item of online content.

Abstract: An environment includes at least two network devices and a plurality of downstream devices or networks. The downstream devices or networks are communicatively coupled to network interfaces of the network devices using a plurality of data cables. The data cables each comprise a switch device configured to switch communication paths to the coupled network devices. Each of the data cables communicatively couple each of the network devices to one of the plurality of downstream devices or networks so that each of the downstream devices or networks has a communications path to each of the network devices and a switchable communications path from each of the network devices. The network devices do not arbitrate active/passive status via direct communication. Based on data contained in a reply packet indicating that a request packet sent by the first network device was acknowledged, the first network device determines that the first network device is an active network device.

Abstract: Systems and methods are provided for generating and operating a speech enhancement model optimized for generating noise-suppressed speech outputs for improved human listening and live captioning. A computing system obtains a speech enhancement model trained on a first training dataset to generate noise-suppressed speech outputs and an automatic speech recognition model trained on a second training dataset to generate transcription labels for spoken language utterances. A third training dataset comprising a set of spoken language utterances is applied to the speech enhancement model to obtain a first noise-suppressed speech output which is applied to the automatic speech recognition model to generate a noise-suppressed transcription output for the set of spoken language utterances.

Abstract: Sending streamed data packets from a producer to a consumer. A method includes, at a first entity, sending consumable data packets from the first entity to a second entity at a first consumable packet rate. The method further includes receiving a first phase delta from the second entity, wherein the first phase delta is computed from transmission jitter, computed from timing information in the consumable data packets. The method further includes sending from the first entity consumable data packets at a second consumable packet rate, the second consumable packet rate being dependent on the first phase delta.

Abstract: Embodiments described herein are directed to intelligently classifying Web trackers in a privacy preserving manner and mitigating the effects of such Web trackers. As users browse the Web and encounter various Web sites, tracker-related metrics are determined. The metrics are obfuscated to protect the privacy of the user. The obfuscated metrics are provided as inputs to a machine learning model, which is configured to output a classification for the Web trackers associated with the Web sites visited by the user. Depending on the classification, the effects of the Web trackers are mitigated by placing restrictions on the Web trackers. The restrictions for a particular Web tracker may be relaxed based on a level of user engagement a user has with respect to the tracker's associated Web site. By doing so, the compatibility risks associated with tracking prevention are mitigated for Web sites that are relatively important to the user.

Abstract: A method for controlling transmission power from one or more radio units is provided including monitoring channel state feedback for a signal communicated between a first radio unit of the one or more radio units and a user device in a transmitted frequency range, wherein the channel state feedback is based at least in part on a metric of quality of the communicated radiofrequency signal, determining that the channel state feedback satisfies a channel state condition, wherein the channel state condition includes a metric to evaluate performance of the one or more radio units relative to the user device based at least on the metric of quality of the communicated signal, and transmitting an instruction to adjust a transmission power in the transmitted frequency range of at least one of the one or more radio units based at least on the satisfaction of the channel state condition.

Abstract: A method, computer program product, and computing system for selecting a reference audio acquisition device from a plurality of audio acquisition devices of an audio recording system. Audio encounter information of the reference microphone may be encoded, thus defining encoded reference audio encounter information. A plurality of acoustic relative transfer functions between the reference microphone and the plurality of audio acquisition devices of the audio recording system may be generated. The encoded reference audio encounter information and a representation of the plurality of acoustic relative transfer functions may be transmitted.

Abstract: A system includes a first sense circuit configured to provide a first output representative of sensed current provided by a first battery coupled to a first load. A second sense circuit is configured to provide a second output representative of sensed current provided by a second battery coupled to the first load. An input current controller is coupled to receive the respective first and second outputs and to couple between the second battery and the first load to control the current provided by the second battery.

Abstract: A system level search module receives system level search user interface registration information for an application of the computing device. The registration information includes an indication of how the system level search module can launch the application. The registration information is added to a registration store, and the application is included as one of one or more applications that can be searched using the system level search user interface.

Abstract: Failover functionality is by identifying at least two network paths for a media communications session between a virtual machine at a computing environment and a client application. Unique Internet Protocol (IP) addresses are assigned for the at least two network paths. Based on application and network metrics at the computing environment, a network condition at the computing environment is determined that is indicative of a performance degradation of the media communications session. A signal is communicated to the client service indicating a switch to a second path of the at least two network paths and a second of the unique IP addresses.

Abstract: A computer system is configured to manage a value of a variable via firmware. Managing the value of the variable includes detecting a system management interrupt (SMI), causing the computer system to enter a system management mode, in which a request associated with the SMI is handled by the firmware. In response to determining that the SMI is generated by a baseboard management controller (BMC) and that a cause thereof is associated with reading or writing a value of a variable, one or more parameters associated with the variable are obtained from the BMC. Based on the cause of the request and the one or more parameters, the value of the variable is read or overwritten with a new value. The value or the new value is then sent to the BMC, which in turn passes the value or new value to a second computer system over a network.

Abstract: Disclosed herein is a system for minimizing the amount of time it takes to process and understand an unstructured, text-heavy document that includes important security-related information. The system uses a model that implements natural language processing techniques to semantically analyze an unstructured, text-heavy document, in order to identify notable security features useable to resolve the security issues in a more effective and efficient manner (e.g., without the need for a technical security professional). More specifically, the system receives an unstructured document that includes text which may be provided by multiple different security providers. The system is configured to apply the model to various text segments (e.g., a phrase, a sentence, a paragraph, etc.) included in the unstructured document to identify notable security features. The model can then associate the notable security features with a prescribed set of mitigation actions that can be implemented to resolve a security issue.

Abstract: A computing system is provided, including a processor and memory storing instructions that cause the processor to execute a domain name service (DNS) log analyzer configured to identify a container identifier associated with a DNS request and a destination IP address associated with a DNS response to the DNS request, using one or more DNS logs, a fleet management system record analyzer configured to identify a first service associated with the container identifier and a second service associated with the destination IP address, using one or more fleet management system logs, and a dependency map generator configured to generate a service-to-service dependency map between the identified first service and the identified second service.

Abstract: Techniques performed by a data processing system for diagnosing problems with a communications platform include obtaining query parameters including an aggregation operator for invoking a machine learning algorithm configured to analyze performance data for the communications platform, automatically executing the query on the performance data to obtain query results by invoking the machine learning algorithm on the performance data to automatically identify a plurality of clusters of data indicative of a performance problem, and presenting a visualization of the query results. The visualization includes indicators identifying cluster properties for which the query results are further refinable and one or more second indicators identifying the second subset of the second cluster properties which are not relevant for further refining the first query results. The indicators are actuatable to automatically update and re-execute the first query based on the respective indicator that is actuated.

Abstract: Techniques for aligning images generated by an integrated camera physically mounted to an HMD with images generated by a detached camera physically unmounted from the HMD are disclosed. A 3D feature map is generated and shared with the detached camera. Both the integrated camera and the detached camera use the 3D feature map to relocalize themselves and to determine their respective 6 DOF poses. The HMD receives the detached camera's image of the environment and the 6 DOF pose of the detached camera. A depth map of the environment is accessed. An overlaid image is generated by reprojecting a perspective of the detached camera's image to align with a perspective of the integrated camera and by overlaying the reprojected detached camera's image onto the integrated camera's image.

Abstract: In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding.

Abstract: An integrated circuit includes a pipeline of compare logic stages. The pipeline, at successive pipeline stages, determines whether each of a set of input symbols meets a corresponding programmable criteria. The compare logic stages each compare the set of input symbols to a respective programmable value. The compare logic stages also each provide, to a respective successive compare logic stage, a corresponding plurality of indicators of whether respective ones of the set of input symbols met the corresponding programmable criteria for that compare logic stage. The corresponding programmable criteria are configurable to be based at least in part on the corresponding plurality of indicators from a respective previous compare logic stage.

Abstract: Example solutions provide saliency for anchor-based object detection, and include: performing, with an object detector, a first object detection process on an image, wherein the first object detection process employs a plurality of anchor boxes; identifying an object detection result for the image; determining, from among the plurality of anchor boxes, a first anchor box associated with the object detection result; and while limiting the object detector to the first anchor box, generating, with the object detector, a saliency map for the image. In some examples, the saliency map is used for selecting further training data for the object detector. In some examples, the saliency map comprises a gradient-based saliency map, and is used for auditing or debugging the object detector.

Abstract: Systems and methods for surfacing natural language queries from one or more transcripts. An example method may include converting received audio to text, through automated speech recognition, to form a transcript of the audio, wherein the transcript includes text of the audio and identifications of speakers associated with portions of the text corresponding to utterances from the respective speakers; generating input signals based on at least the transcript; executing at least one of one or more heuristics or a trained machine-learning (ML) model, using the generated input signals as an input, to generate at least one of a suggested natural language query for searching the transcript or a key moment within the received audio; and causing at least one of the suggested natural language query or the key moment to be surfaced on one or more remote devices.

Abstract: Techniques for providing adaptive assistive technology for assisting users with visual impairment can be used on a computing device. These techniques include displaying content to a user, capturing a series of images or video of the user using a camera, analyzing the series of images or video to determine whether the user is exhibiting behavior or characteristics indicative of visual impairment, and rendering a magnification user interface on the display configured to magnify at least a portion of the content of the display based on a determination that the user is exhibiting behavior or characteristics indicative of visual impairment. The magnification user interface may be controlled based on head and/or eye movements of the user of the computing device.

Abstract: Systems and methods are provided performing for low compute depth map generation by implementing acts of obtaining a stereo pair of images of a scene, downsampling the stereo pair of images, generating a depth map by stereo matching the downsampled stereo pair of images, and generating an upsampled depth map based on the depth map using an edge-preserving filter for obtaining at least some data of at least one image of the stereo pair of images.

Abstract: The techniques disclosed herein enable a system to perform a robust evaluation of resource requirement recommendations through a simulated computing environment that closely resembles current conditions of a live computing environment. To achieve this, system characteristics such as CPU, RAM, and storage are extracted from currently available computing resources at the live computing environment. In addition, active software deployments at the live computing environment are randomly sampled to generate an activity dataset. The system characteristics and the activity dataset are then used to generate the simulated computing environment. Instances of a pending software deployment are then assigned to the simulated computing environment according to a resource requirement recommendation. The instances are then executed across various scenarios and analyzed to calculate a level of resource utilization.

Abstract: A digital assistant supported on devices such as smartphones, tablets, personal computers, game consoles, etc. includes an extensibility client that exposes an interface and service that enables third party applications to be integrated with the digital assistant so the application user experiences are rendered using the native voice of the digital assistant. Specific voice inputs associated with a given application may be registered by developers using a manifest that is loaded when the application is launched on the device so that voice inputs from the device user can be mapped by the digital assistant extensibility client to the appropriate application as input events for consumption. In typical implementations, the manifest is arranged as a declarative document that streamlines application development and provides a seamless user experience by enabling customization of third party applications to integrate the digital assistant's voice and behaviors within the user experience of the application's domain.

Abstract: Described herein is a system and method for validating media integrity using asymmetric key cryptography utilizing a public/private cryptographic key pair. The private key is kept secret and is known to an originator and/or publisher of a media file. The public key is added to the media file and is used to validate integrity of the media file, that is, that content of the media file (e.g., portion(s), frame(s)) has not been altered since publication of the media file. By validating integrity of the media file, strong proof that the media file came from an owner of the keypair (e.g., had possession of the private key) can be obtained, for example, resolving issues of trust and/or authenticity common in altered content. In some embodiments, information regarding an origin of the content can further be determined.

Abstract: Examples of the present disclosure describe systems and methods for generating multiple semantic hypotheses for search query intent understanding. In aspects, a search query may be received by a query analysis component associated with a search system. The query analysis component may be used to evaluate the search query for ambiguity in the domain, intent, and/or slot(s) of the search query. A set of hypotheses representing for one or more combinations of the domain, intent, and/or slot(s) of the search query may be generated. The set of hypotheses may be scored and/or ranked. Based on the scores/ranks, one or more of the hypotheses in the set of hypotheses may be provided to a user and/or one or more processing components accessible to the search system.

Abstract: An online meeting system begins the process of connecting a user to an online meeting when a request is received from a user to start or join the online meeting. In response to the request, a pre-meeting user interface (UI) is displayed having a user interface control which, when activated, enables transmission of audio and/or video data for the online meeting, and prior to activation of the control, connection parameters are shared with an online meeting service to preheat the meeting. In response to activation of the control, transmission of audio and/or video data for the online meeting is enabled.

Abstract: Embodiments are associated with a speaker-independent attention-based encoder-decoder model to classify output tokens based on input speech frames, the speaker-independent attention-based encoder-decoder model associated with a first output distribution, and a speaker-dependent attention-based encoder-decoder model to classify output tokens based on input speech frames, the speaker-dependent attention-based encoder-decoder model associated with a second output distribution. The second attention-based encoder-decoder model is trained to classify output tokens based on input speech frames of a target speaker and simultaneously trained to maintain a similarity between the first output distribution and the second output distribution.

Abstract: An allowed client server, that is authorized to access a resource server over a given port, receives a client request, from a client computing system, to access the resource server. The allowed client server authenticates and authorizes the request, using an authentication and authorization mechanism, and selects a port with which to communicate with the client computing system. The identity of that port is provided to the client computing system, and a port forwarding mechanism forwards traffic between the client computing system and the resource server, through the client-facing port and to the given port on the resource server.

Abstract: Systems are provided for logging transactions in heterogeneous networks that include a combination of one or more instrumented components and one or more non-instrumented components. The instrumented components are configured to generate impersonated log records for the non-instrumented components involved in the transaction processing hand-offs with the instrumented components. The impersonated log records are persisted with other log records that are generated by the instrumented components in a transaction log that is maintained by a central logging system to reflect a complete flow of the transaction processing performed on the object, including the flow through the non-instrumented component(s).