Abstract: Systems and techniques for validation and generation of localized content for audio and video are described herein. The systems and techniques provide for training of twin neural networks to evaluate performance characteristics, sometimes referred to as content-auxiliary characteristics, of a localized performance. The localized performance may be validated or improved by identifying misalignment in the performance characteristics to ensure that localized content preserves content as well as creative intent and performance ability in the final product. The machine learning models trained using the techniques described herein may be used in connection with auto-localization processes to automatically generate high quality localized audio and video content.

Abstract: Systems, devices, and methods are provided for multi-stem volume equalization, wherein the volume levels of each stem may be adjusted non-uniformly. Audio may be diarized into a plurality of stems, including background noise separate. Mean and variance of the volume levels of the stems may be computed. Each audio stem may be automatically adjusted based on a stem-specific preference that a user may specify. View may adjust actor volume relative to the mean/variance that maintains a relative difference in volume levels between stems.

Abstract: Techniques are generally described for causal impact estimation using machine learning. A first machine learning model is trained using non-treatment variables during training. A second machine learning model uses learned weights from the first machine learning model for non-treatment variables and is trained on one or more treatment variables. The second machine learning model estimates outcomes based on the presence or absence of an event represented by the treatment variable. Selection bias is reduced by warm-starting the second machine learning model with non-treatment variable weights learned during training of the first machine learning model.

Abstract: Prediction of outcomes of disruptive treatments are enabled utilizing sequenced training of a machine learning model over ordered bins of treatment candidates. Treatment candidates may be assigned to candidate characterization bins with an ordering, and the model may be trained with a sequence of training steps corresponding to the ordering of the candidate characterization bins, in each training step the model having untreated candidate features from a corresponding bin and aggregate metrics from one or more previous steps as input. The predicted outcome for a selected bin may be generated with the trained model having treated candidate features and aggregate metrics from one or more previous steps as input. The predicted outcome may be a counterfactual prediction for a bin with insufficient control candidates, and may represent a nonlinear extrapolation from control data in prior bins in the bin ordering.

Abstract: Model-based dubbing techniques are implemented to generate a translated version of a source video. Spoken audio portions of a source video may be extracted and semantic graphs generated that represent the spoken audio portions. The semantic graphs may be used to produce translations of the spoken portions. A machine learning model may be implemented to generate replacement audio for the spoken portions using the translation of the spoken portion. A machine learning model may be implemented to generate modifications to facial image data for a speaker of the replacement audio.

Abstract: Audio content and played frames may be received. The audio content may correspond to first video content. The played frames may be included in the first video content. The first video content may further include a replaced frame. The played frames and the replaced frame may include a face of a person. Location data may also be received that indicates locations of facial features of the face of the person within the replaced frame. A replacement frame may be generated, such as by rendering the facial features in the replacement frame based at least in part on the locations indicated by the location data and positions indicated by a portion of the audio content that is associated with the replaced frame. Second video content may be played including the played frames and the replacement frame. The replacement frame may replace the replaced frame in the second video content.

Abstract: An approximate count of a subset of records of a data set is obtained using one or more transformation functions. The subset comprises records which contain a first value of one input variable, a second value of another input variable, and a particular value of a target variable. Using the approximate count, an approximate correlation metric for a multidimensional feature and the target variable is obtained. Based on the correlation metric, the multidimensional feature is included in a candidate feature set to be used to train a machine learning model.

Abstract: Systems and methods are provided for using a machine learning model to analyze customers data for each of a number of customers interacting with electronic commerce, and determining whether the customers are high value customers. For the high value customers, one or more high value actions are then determined by the machine learning model, the one or more high value actions representing actions previously performed by or with respect to the customers and that correlate with a likelihood of the customers reaching high value customers status. Non-high value customers may then be prompted to perform the high value action which may elevate the non-high value customers to high value customers status.

Abstract: Techniques for generating an automated guide for exploring content of a content streaming platform based on inferred intent are described herein. For example, click stream data from interactions with a content streaming platform during a session, along with historical click stream data of historical interactions with the content streaming platform during historical sessions may be obtained. A score for each piece of content from a plurality of content offered by the content streaming platform may be determined based on the click stream data and the historical click stream data. The plurality of content may be ranked based on the associated scores for each piece of content. Media content may be generated that includes a portion of an associated trailer from a subset of the ranked plurality of content based on the score for each piece of content of the subset. The media content may be presented via a user interface.

Abstract: A content provider may cause a client device of a user to output a personalized puzzle in response to receiving a request from the client device to access electronic content of the content provider. The puzzle may include a theme that corresponds to a determined predilection of the user, and/or the puzzle may be a type of puzzle that corresponds to the user's predilection. The client device may also output, with the puzzle, an incentive for completing (e.g., solving) the puzzle Upon receiving data indicating that the user has completed his/her personalized puzzle, the content provider may provide the reward to the user.

Abstract: In a machine learning environment, missing values can be imputed based upon an expectation maximization style approach. A system partitions a dataset, and uses a first partition as a training subset and a second partition as a verification subset. The training subset is used to train a machine learning model, which is then used to impute missing values in the second subset. The subsets may be swapped and the process iterates to predict missing values in the dataset with a high degree of accuracy, thereby improving both the accuracy of the machine learning model and the accuracy of the imputed values. The noise in the value prediction is reduced through a linear regression setting to account for heterogeneity in the dataset.

Abstract: Systems and methods are provided for learning and using a linear machine learning model, where the training data includes a categorical variable. After encoding the categorical variable, a computing system can learn a linear machine learning model. From the linear machine learning model, the computing system can construct a numeric variable. The numeric variable can be used in computing a prediction result and in learning a new linear machine learning model.

Abstract: A network device operable as a provide edge router is described. The network device comprises one or more processors operably coupled to a memory; a configuration interface configured for execution by the one or more processors to receive configuration data configuring the network device as a provider edge router of an intermediate layer 3 network to provide multi-homed layer 2 virtual bridge connectivity to a customer edge device using an active-standby mode of operation; and a routing process configured for execution by the one or more processors to send, to a remote provider edge router in response to determining the network device is able to send layer 2 packets to the customer edge device, a route advertisement that includes a static route specifying a layer 3 address of the customer edge device as a next-hop for a layer 3 subnet.

Abstract: A network device operable as a provide edge router is described. The network device comprises one or more processors operably coupled to a memory; a configuration interface configured for execution by the one or more processors to receive configuration data configuring the network device as a provider edge router of an intermediate layer 3 network to provide multi-homed layer 2 virtual bridge connectivity to a customer edge device using an active-standby mode of operation; and a routing process configured for execution by the one or more processors to send, to a remote provider edge router in response to determining the network device is able to send layer 2 packets to the customer edge device, a route advertisement that includes a static route specifying a layer 3 address of the customer edge device as a next-hop for a layer 3 subnet.

Abstract: An example router includes a control unit configured to receive virtual private network (VPN) routing and forwarding table (VRF) configuration data defining a VRF for a VPN and VPN address space for the VPN, receive configuration data defining a measurement endpoint for measuring performance of a layer 3 (L3) service and associating the measurement endpoint with a remote measurement endpoint of a remote router. The control unit is configured to encapsulate, to generate a flow measurement packet, a layer 2 (L2) measurement packet in a layer 4 (L4) header and an L3 header, where the L3 header includes a source L3 address within the VPN address space and associated with the measurement endpoint, and where the L3 header includes a destination L3 address within the VPN address space and associated with the remote measurement endpoint. The control unit is configured to output the flow measurement packet to the remote router.

Abstract: An improved technique involves automatically applying a mapping from anomalous values of a parameter that describes the performance of a component to a defect in the component. As part of operations of a data storage system, a computer collects data related to performance metrics of components of the data storage system. Upon receiving the data, the computer determines sequences of values of the performance metrics that indicate anomalous behavior of the component. The computer than maps these values to a defect of the component, and performs a corrective operation on the component to correct the defect.

Abstract: An improved technique involves mapping differences between current data collected from a component and previous data collected from the component to anomalous behavior of the component. A central diagnosis server collects previous state data such as disk or CPU utilization from components of various data storage systems it supports. The server may store this data, indexed by identifiers such as events linked to the state data, in a central database for later reference. The server then compares current state data being received from a particular data storage system to previous state data stored in the database. In some arrangements, the server selects previous state data based on matching event identifiers corresponding to the current state data and previous state data. The central diagnosis server then determines anomalous behavior based on the difference between current and previous state data.

Abstract: A novel canola variety designated 46H75 and seed, plants and plant parts thereof, produced by crossing Pioneer Hi-Bred International, Inc. proprietary inbred canola varieties. Methods for producing a canola plant that comprises crossing canola variety 46H75 with another canola plant. Methods for producing a canola plant containing in its genetic material one or more traits introgressed into 46H75 through backcross conversion and/or transformation, and to the canola seed, plant and plant part produced thereby. This discovery relates to the canola variety 46H75, the seed, the plant produced from the seed, and variants, mutants, and minor modifications of canola variety 46H75. This discovery further relates to methods for producing canola varieties derived from canola variety 46H75.

Abstract: A novel canola variety designated VR 9560 CL and seed, plants and plant parts thereof, produced by crossing Pioneer Hi-Bred International, Inc. proprietary inbred canola varieties. Methods for producing a canola plant that comprises crossing canola variety VR 9560 CL with another canola plant. Methods for producing a canola plant containing in its genetic material one or more traits introgressed into VR 9560 CL through backcross conversion and/or transformation, and to the canola seed, plant and plant part produced thereby. This discovery relates to the canola variety VR 9560 CL, the seed, the plant produced from the seed, and variants, mutants, and minor modifications of canola variety VR 9560 CL. This discovery further relates to methods for producing canola varieties derived from canola variety VR 9560 CL.