Abstract: Acoustic echo cancellation for a video conference system is described. A location of a person in a room can be determined. An audio signal received from the location of the person can be captured using beamforming. An acoustic echo cancellation parameter can be determined based in part on the audio signal captured from the location of the person. Acoustic echo cancellation can be performed on the audio signal using the acoustic echo cancellation parameter.

Abstract: Structures for a memory device and methods of forming a structure for a memory device. The structure includes a first and second source/drain regions in a semiconductor substrate, a first gate stack on the semiconductor substrate, and a second gate stack on the semiconductor substrate adjacent to the first gate stack. The first and second gate stacks are positioned in a lateral direction between the first source/drain region and the second source/drain region. The first gate stack includes first and second gate electrodes, and the first gate electrode includes segments spaced apart along a longitudinal axis of the first gate stack.

Abstract: Systems and methods for identifying data of interest are disclosed. The system may retrieve unstructured data from an internet data source via an alert system or RSS feed. The system may input the unstructured data into various models and scoring systems to determine whether the data is of interest. The models and scoring systems may be executed in order or in parallel. For example, the system may input the unstructured data into a Naïve Bayes machine learning model, a long short-term memory (LSTM) machine learning model, a named entity recognition (NER) model, a semantic role labeling (SRL) model, a sentiment scoring algorithm, and/or a gradient boosted regression tree (GBRT) machine learning model. Based on determining that the unstructured data is of interest, a data alert may be generated and transmitted for manual review or as part of an automated decisioning process.

Abstract: An apparatus includes a support, a first camera, and second camera, and a processor. The support is configured to be mounted to a head of a user. The first camera is mounted on the support and positioned to capture a first image of a face of the user. The second camera is mounted on the support and positioned to capture a second image of the face of the user that is non-overlapping with the first image. The processor is mounted to the support and programmed to stitch the first image and the second image together to construct an image of the face of the user.

Abstract: Systems and methods for identifying data of interest are disclosed. The system may retrieve unstructured data from an internet data source via an alert system or RSS feed. The system may input the unstructured data into various models and scoring systems to determine whether the data is of interest. The models and scoring systems may be executed in order or in parallel. For example, the system may input the unstructured data into a Naïve Bayes machine learning model, a long short-term memory (LSTM) machine learning model, a named entity recognition (NER) model, a semantic role labeling (SRL) model, a sentiment scoring algorithm, and/or a gradient boosted regression tree (GBRT) machine learning model. Based on determining that the unstructured data is of interest, a data alert may be generated and transmitted for manual review or as part of an automated decisioning process.

Abstract: Examples of machine learning model training are described herein. In some examples, a method may include training, on an apparatus, an encoder machine learning model or a context machine learning model. In some examples, the method may include training the encoder machine learning model or the context machine learning model using negative samples in a latent space from emote devices and a ground truth.

Abstract: Examples of computing task scheduling based on an intrusiveness metric are described. In an example, an intrusiveness metric that indicates an impact of a computing task on performance of a computing device may be determined with an intrusiveness machine learning model. The intrusiveness metric may be sent to a scheduler device to determine distribution of additional computing tasks according to a scheduling machine learning model.

Abstract: According to aspects of the present disclosure there are provided methods and apparatus for providing a user-centric application comprising a plurality of service modules, the method comprising identifying available resources associated with each of a plurality of edge devices in the local network, identifying a first device of the local network, the first device offering a user input service, identifying a second device of the local network, the second device to receive an output event and present the output event for consumption by the user, for each service module, each service module to provide a portion of a functionality of the user-centric application and having an associated resource request, deploying the service module to an edge device based on the associated resource request and the identified available resources, and configuring data flows between the deployed service modules, the first device, and the second device to realize the user-centric application.

Abstract: Examples of methods for controlling machine learning model structures are described herein. In some examples, a method includes controlling a machine learning model structure. In some examples, the machine learning model structure may be controlled based on an environmental condition. In some examples, the machine learning model structure may be controlled to control apparatus power consumption associated with a processing load of the machine learning model structure.

Abstract: An example device includes a main display panel that includes a main array of pixels and an opening within the main array of pixels. The example device further includes a beam splitter positioned to communicate light through the opening within the main array of pixels, a sensor positioned with respect to the beam splitter to capture light incident on the opening within the main array of pixels, and a subarray including a pixel. The subarray is positioned with respect to the beam splitter to output light through the opening within the main array of pixels.

Abstract: In example implementations, a device is provided. The device includes a microphone, an event generator, a keyword detector, and a digital signal processor. The digital signal processor is in communication with the keyword detector. The microphone is to receive an audio signal. The event generator generates a pattern of events from the audio signal. The keyword detector detects a keyword based on the pattern of events generated by the event generator. In response to the keyword being detected, the digital signal processor is activated to analyze subsequent audio streams.

Abstract: Systems and methods for identifying data of interest are disclosed. The system may retrieve unstructured data from an internet data source via an alert system or RSS feed. The system may input the unstructured data into various models and scoring systems to determine whether the data is of interest. The models and scoring systems may be executed in order or in parallel. For example, the system may input the unstructured data into a Naive Bayes machine learning model, a long short-term memory (LSTM) machine learning model, a named entity recognition (NER) model, a semantic role labeling (SRL) model, a sentiment scoring algorithm, and/or a gradient boosted regression tree (GBRT) machine learning model. Based on determining that the unstructured data is of interest, a data alert may be generated and transmitted for manual review or as part of an automated decisioning process.

Abstract: Examples disclosed herein provide the ability for a computing device to adjust settings on a computing device. In one example method, the computing device captures, via a first sensor of a computing device, images of an environment that the computing device is currently in, and detects objects in the environment as captured by the images. As an example, the computing device determines a location of the environment based on contextual data gathered from the detected objects and adjusts a setting on the computing device based on the determined location.

Abstract: A computer device including an integrated input device is provided. The integrated input device includes a positive disconnect system including a display of an open connection to the integrated input device when the integrated input device is deactivated. The open connection comprises a visible metal trace on a line coupling the integrated input device to the computer device.

Abstract: In some examples, adaptive speech intelligibility control for speech privacy may include determining, based on background noise at a near-end of a speaker, a noise estimate associated with speech emitted from the speaker, and comparing, by using a specified factor, the noise estimate to a speech level estimate for the speech emitted from the speaker. Adaptive speech intelligibility control for speech privacy may further include determining, based on the comparison, a gain value to be applied to the speaker to produce the speech at a specified level to maintain on-axis intelligibility with respect to the speaker, and applying the gain value to the speaker.

Abstract: A communication system may include, in an example, a first computing device communicatively coupled, via a network, to at least a second computing device maintained at a geographically distinct location than the first computing device; the first computing device including: an array of audio output devices and a processor to receive transmitted speech data and metadata describing an estimated direction of arrival (DOA) of speech from a plurality of speakers at an array of microphones at the second computing device and render audio at the array of audio output devices associated with the first computing device by eliminating spatial collision during rendering; said spatial collision arising due to the low angular separation of the estimated DOA of a plurality of speakers.

Abstract: A trace history generation method includes receiving from an originating participant in a custody chain of transactions of an asset, by an intermediate participant, a trace history request for the asset. The request has an identification of an owner, data identifying the asset and a parent transaction identification in association with another of the participants, and a hash of the data. Thereafter, an identifier is assigned for the request and the request verified by interrogating a blockchain with the hash. Upon verification, a trace history document is generated including the data identifying the asset, an identifier of the intermediate participant, and a disposition of the asset including an identifier of a next nearest participant. A hash is computed for the trace history and a blockchain transaction performed recording and storing the hash in connection with the assigned identifier. Finally, the document is transmitted to the originating participant.

Abstract: For each of a number of workloads, time intervals within execution performance information that was collected during execution of the workload on a first hardware platform are correlated with corresponding time intervals within execution performance information that was collected during execution of the workload on a second hardware platform. For a workload, the time intervals within the execution performance information on the second hardware platform are correlated to the time intervals within the execution performance information the first hardware platform during which the same parts of the workload were executed. A machine learning model that outputs predicted performance on the second hardware platform relative to known performance on the first hardware platform is trained. The model is trained from the correlated time intervals within the execution performance information for each workload on the hardware platforms.

Abstract: An apparatus includes a support, a first camera, and second camera, and a processor. The support is configured to be mounted to a head of a user. The first camera is mounted on the support and positioned to capture a first image of a face of the user. The second camera is mounted on the support and positioned to capture a second image of the face of the user that is non-overlapping with the first image. The processor is mounted to the support and programmed to stitch the first image and the second image together to construct an image of the face of the user.

Abstract: A communication system may include, in an example, a first computing device communicatively coupled, via a network, to at least a second computing device maintained at a geographically distinct location than the first computing device; the first computing device including: an array of audio output devices and a processor to receive transmitted speech data and metadata describing an estimated direction of arrival (DOA) of speech from a plurality of speakers at an array of microphones at the second computing device and render audio at the array of audio output devices associated with the first computing device by eliminating spatial collision during rendering; said spatial collision arising due to the low angular separation of the estimated DOA of a plurality of speakers.