Abstract: Systems and methods for presence ground truth approximation and utilization are disclosed. For example, a system detects the presence of a predefined subject, such as a person associated with a given user profile, and/or determines that authentication criteria for performing an action in association with the user profile has been satisfied. A period of time to associate data is determined, and data of one or more data types is labeled as being associated with the speaker identification event. That data may be formatted and input into one or more models to train those models to more accurately detect presence and/or determine whether authentication of a user profile should succeed.

Abstract: In some implementations, a device may retrieve, from a user database, information identifying a plurality of users that are to be subjected to an adverse action. The device may retrieve, from an event stream, event data relating to an incident that has affected an affected area, where the event data indicates at least a location of the affected area. The device may identify, based on the information identifying the plurality of users, one or more users of the plurality of users that reside in the location of the affected area. The device may cause transmission of communications relating to the adverse action for each of the plurality of users, except for the one or more users that reside in the location of the affected area.

Abstract: A conditional adversarial latent model (CALM) process can be used to generate reference motions from a set of original reference movements to create a library of new movements for an agent. The agent can be a virtual representation various types of characters, animals, or objects. The CALM process can receive a set of reference movements and a requested movement. An encoder can be used to map the requested movement onto a latent space. A low-level policy can be employed to produce a series of latent space joint movements for the agent. A conditional discriminator can be used to provide feedback to the low-level policy to produce stationary distributions over the states of the agent. A high-level policy can be employed to provide a macro movement control over the low-level policy movements, such as providing direction in the environment. The high-level policy can utilize a reward or a finite-state machine function.

Abstract: In various examples, systems and methods are disclosed relating to generating a simulated environment and update a machine learning model to move each of a plurality of human characters having a plurality of body shapes, to follow a corresponding trajectory within the simulated environment as conditioned on a respective body shape. The simulated human characters can have diverse characteristics (such as gender, body proportions, body shape, and so on) as observed in real-life crowds. A machine learning model can determine an action for a human character in a simulated environment, based at least on a humanoid state, a body shape, and task-related features. The task-related features can include an environmental feature and a trajectory.

Abstract: In various examples, artificial intelligence (AI) agents can be generated to synthesize more natural motion by simulated actors in various visualizations (such as video games or simulations). AI agents may employ one or more machine learning models and techniques, such as reinforcement learning, to enable synthesis of motion with enhanced realism. The AI agent can be trained based on widely-available broadcast video data, without the need for more costly and limited motion capture data. To account for the lower quality of such video data, various techniques can be employed, such as taking into account the motion of joints, and applying physics-based constraints on the actors, resulting in higher quality, more lifelike motion.

Abstract: A multidimensional equalizer and cross talk canceller for a communication network that simultaneously removes far end cross talk NEXT) and intersymbol interference (ISI) from a received signal. A multidimensional-pair channel is treated as a single multidimensional channel and a receiver in the communication network equalizes received signals through the use of the multidimensional equalizer. A decision feedback equalizer determines a multidimensional steepest descent gradient to adjust matrix coefficients.

Abstract: A simulation system is provided for simulating behavior of a device for implementing an algorithm using a software model and a hardware model which are converted to a common programming language and mathematical notation. The simulation system uses the same input user interface for the software model and the hardware model. Further, the simulation system uses the same output user interface for generating the simulation results for both the software model and the hardware model in the common programming language and mathematical notation, thereby allowing a user to easily verify and analyze the software and hardware simulation results for optimization of the device.

Abstract: A system comprises an enhanced downsampling operation for digital data. In the preferred embodiment, a downsampling filter has a quantity of filter coefficients equal to 4(a)+1, where (a) is an integer. In this case the even-numbered coefficients are, to the degree of accuracy required, equal to zero. Also the central even-numbered coefficient is equal to ½. As multiplication by ½ in a binary digital system may be executed by a simple right shift, the total number of coefficient-sample multiplications may be reduced to 2(a). The filter design wherein the even-numbered coefficients equal zero also has the additional benefit of reducing the number of storage locations for the filter coefficients. A further aspect of the present invention is the segregation of the input data stream into even and odd-numbered sample buffers.

Abstract: A system and method to manipulate information in an audio decoder, the system having a demultiplexer to separate the information into packets of audio data and packet parameters, a control manager for controlling the packet parameters, and an audio decoder to manipulate the packets of audio data in response to the packet parameters. The invention also includes a control processor for passing host parameters to the control manager and a digital-to-analog converter to convert the audio information from a digital signal to an analog signal.

Abstract: A platform-independent software-implemented digital signal processing system in a computer system. The digital signal processing system is comprised of a digital signal processing unit implemented in C program code which receives data and applies a process to generate therefrom a computer file representative of a processed response. The digital signal processing system also is comprised of a graphical user interface implemented in Java program code, which generates two-dimensional graphic images and text on the computer system's user output device, and is for receiving user-selected process parameters and for displaying the results of the processed response. In addition, the digital signal processing system is comprised of an interface code which provides communication between the graphical user interface and the digital signal processing unit.