Abstract: A method of generating a simulated image for training a model to detect resident space objects (RSOs), a method of training the model, and a method of detecting RSOs are provided. The method includes generating a foreground of the simulated image including RSOs by calculating coordinates of an imaging satellite at a given time, determining an area of interest given a field of view (FOV) of the imaging satellite, and calculating coordinates of all RSOs and saving the coordinates if the RSO is within the area of interest. The method further includes generating a background of the simulated image including stars by querying a star catalogue database for coordinates of all stars that fall inside the FOV, adding noise, and translating RSO and star coordinates to pixel coordinates. The method further includes generating the simulated image by choosing an imaging mode, setting an exposure time, and rendering the simulated image.

Abstract: A method for determining regression of a database query associated with a first execution plan includes receiving a first performance measure for the database query and the first execution plan; determining a presence of at least one stored performance measure for the database query in a data repository; adding the first performance measure and identifiers for the database query and the first execution plan to a synchronization list; retrieving a second performance measure associated with a second execution plan from the data repository; determining a regression of the database query by comparing the first performance measure to the second performance measure; in response to a determination that the database query is regressed, adding the first performance measure, the second performance measure, and identifiers for the database query and the first execution plan to a regression report.

Abstract: A computer mediated communication system includes a plurality of communication devices, a wireless transceiver, a computer system configured to wirelessly communicate with the communication devices via the wireless transceiver and mediate communications among the communication devices. The computer system a memory coupled with a processor.

Abstract: In a method for managing and distributing content in a plurality of observation platforms, a message is generated at a cloud based component of a content distribution manager in response to user interaction via an interface of the content distribution manager. Responsive to the user interactions and to interactions of third party software via an application program interface with the cloud based component, delivery of the message is scheduled and a plurality of specified devices belonging to a specified class of employees are specified for delivery in a plurality of observation platforms at a designated time and location via the cloud based component. The plurality of observation platforms are located in a plurality of different enterprise locations. The message is delivered to the plurality of observation platforms which relay the message to the plurality of specified devices.

Abstract: Systems, apparatus, and methods are provided that identify a querying user's top peers, recommends an optimal product interaction journey, and tracks the value delivered. Peers of the querying user are identified based on the common profile attributes, product interaction, and similar user initiatives. A champion peer is recommended by sorting the peers based on the cumulative quality of product interactions which is modeled by a learnable parametric equation. A metric is formulated by measuring the value delivered to the user by computing the number of product interactions aligning to the user's initiative. Most engaging product interactions (e.g., documents read, events attended) by the champion peer aligning to querying user's initiatives are identified and are recommended to the querying user as a product interaction journey.

Abstract: A joint segmenting and ASR model includes an encoder to receive a sequence of acoustic frames and generate, at each of a plurality of output steps, a higher order feature representation for a corresponding acoustic frame. The model also includes a decoder to generate based on the higher order feature representation at each of the plurality of output steps a probability distribution over possible speech recognition hypotheses, and an indication of whether the corresponding output step corresponds to an end of segment (EOS).

Abstract: In a method of query derivation in an observation platform a signal from a first communication device is received at a second communication device that is associated with a computer system. The computer system is associated with an organization and a first characteristic of the signal corresponds to an audible source. The signal is parsed, by the computer system according to a policy, to determine metadata associated with the signal, wherein the first communication device is operated by a user and wherein the policy dictates rules for use of the metadata. The computer system determines a prior user history of the user. The computer system converts the audible source of the signal to text or machine understandable language. The computer system derives a query related to the organization based on at least one of the prior user history, the metadata, and the text or machine understandable language.

Abstract: Generally, the present disclosure is directed to enhanced federated learning (FL) that employs a set of clients with varying amounts of computational resources (e.g., system memory, storage, and processing bandwidth). To overcome limitations of conventional FL methods that employ a set of clients with varying amounts of computational resources, the embodiments run multi-directional knowledge distillation between the server models produced by each federated averaging (FedAvg) pool, using unlabeled server data as the distillation dataset. By co-distilling the two (or more) models frequently over the course of FedAvg rounds, information is shared between the pools without sharing model parameters. This leads to increased performance and faster convergence (in fewer federated rounds).

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

Abstract: Information can be distilled from a global automatic speech recognition (ASR) model to a client ASR model. Many implementations include using an RNN-T model as the ASR model, where the global ASR model includes a global encoder, a joint network, a prediction network, and where the client ASR model includes a client encoder, the joint network, and the prediction network. Various implementations include using principal component analysis (PCA) while training the global ASR model to learn a mean vector and a set of principal components corresponding to the global ASR model. Additional or alternative implementations include training the client ASR model to generate one or more predicted coefficients of the global ASR model.

Abstract: In a method of managing emergency management information within an observation platform an emergency management and response application is provisioned at an observation platform. The provisioning is administered by a cloud services platform and includes configuration and deployment of the emergency management and response application within the observation platform. In response to receipt at the observation platform of a report of an emergency, operation of the emergency management and response application is triggered within the observation platform. Emergency management information is sent, via the emergency management and response application, to a group of users of the observation platform. The emergency management information includes at least one of an alert related to the emergency and instructions related to the emergency.

Abstract: Automated mocking of computer system deployments is facilitated. A method as described herein can include associating, by a first system operatively coupled to a processor, respective properties of a first deployment of a second system on a first computing device with respective automation mapping functions; executing, by the first system, the automation mapping functions in an order defined by dependencies between respective ones of the automation mapping functions, resulting in a series of system modeling tasks and an order associated with the series of system modeling tasks; and performing, by the first system, the series of system modeling tasks in the order associated therewith, resulting in a second deployment of the second system being created on a second computing device that is distinct from the first computing device.

Abstract: In a method of observation platform collaboration integration, a collaboration application is provisioned at an observation platform. The provisioning is administered by a cloud services platform in collaboration with a computer system of the observation platform and includes configuration and deployment of the collaboration application within the observation platform. An automation software component is sent from the collaboration application for resident installation at an external collaboration application which is external to an environment of the observation platform. The automation software component organizes information in the external retailer system for exchange, via a cloud-based gateway, with the collaboration application. The collaboration application is communicatively coupled, via the cloud-based gateway, with the external collaboration application. User information and task information are synchronized between the collaboration application and the external collaboration application.

Abstract: A method includes receiving a training dataset that includes one or more spoken training utterances for training an automatic speech recognition (ASR) model. Each spoken training utterance in the training dataset paired with a corresponding transcription and a corresponding target sequence of auxiliary tokens. For each spoken training utterance, the method includes generating a speech recognition hypothesis for a corresponding spoken training utterance, determining a speech recognition loss based on the speech recognition hypothesis and the corresponding transcription, generating a predicted auxiliary token for the corresponding spoken training utterance, and determining an auxiliary task loss based on the predicted auxiliary token and the corresponding target sequence of auxiliary tokens. The method also includes the ASR model jointly on the speech recognition loss and the auxiliary task loss determined for each spoken training utterance.

Abstract: In a method of determining and sharing proximity of device users within an environment of an observation platform, the observation platform determines that a first communication device associated with a first user is in the environment of the observation platform. The observation platform detects that the first communication device is in proximity to a second communication device associated with a second user. Responsive to the detection, the observation platform generates proximity information for the first user and the second user. The observation platform relays the proximity information to a second observation platform via a computer network, wherein a second environment of the second observation platform is separate from the environment of the observation platform.

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

Abstract: In a method of query derivation in an observation platform a signal from a first communication device is received at a second communication device that is associated with a computer system. The computer system is associated with an organization and a first characteristic of the signal corresponds to an audible source. The signal is parsed, by the computer system according to a policy, to determine metadata associated with the signal, wherein the first communication device is operated by a user and wherein the policy dictates rules for use of the metadata. The computer system determines a prior user history of the user. The computer system converts the audible source of the signal to text or machine understandable language. The computer system derives a query related to the organization based on at least one of the prior user history, the metadata, and the text or machine understandable language.

Abstract: Implementations disclosed herein are directed to a hybrid federated learning (FL) technique that utilizes both federated averaging (FA) and federated distillation (FD) during a given round of FL of a given global machine learning (ML) model. Implementations may identify a population of client devices to participate in the given round of FL, determine a corresponding quantity of instances of client data available at each of the client devices that may be utilized during the given round of FL, and select different subsets of the client devices based on the corresponding quantity of instances of client data. Further, implementations may cause a first subset of the client devices to generate a corresponding FA update and a second subset of client devices to generate a corresponding FD update. Moreover, implementations may subsequently update the given global ML model based on the corresponding FA updates and the corresponding FD updates.

Abstract: In a method of moderating action requests and structured communications within an observation platform, in response to a request interaction a computer system sets up an action request regarding a structured communication in the observation platform. The computer system analyzes the action request with respect to context in the observation platform, where the context is one of user context in the observation platform and device context in the observation platform. The computer system analyzes the action request with respect to status in the observation platform, where the status is one of user status in the observation platform and device status in the observation platform. The computer system moderates an action in the observation platform with respect to the structured communication based on results of the context and status analyses.

Abstract: In a method of observation platform collaboration integration, a collaboration application is provisioned at an observation platform. The provisioning is administered by a cloud services platform in collaboration with a computer system of the observation platform and includes configuration and deployment of the collaboration application within the observation platform. An automation software component is sent from the collaboration application for resident installation at an external collaboration application which is external to an environment of the observation platform. The automation software component organizes information in the external retailer system for exchange, via a cloud-based gateway, with the collaboration application. The collaboration application is communicatively coupled, via the cloud-based gateway, with the external collaboration application. User information and task information are synchronized between the collaboration application and the external collaboration application.