Abstract: The invention integrates emerging applications, tools and techniques for machine learning in medicine with videoconference networking technology in novel business methods that support rapid adaptive learning for medical minds and machines. These methods can leverage domain knowledge and clinical expertise with networked cognitive collaboration, augmented clinical intelligence and cybernetic workflow streams for learning health care systems. The invention enables multimodal clinical communications, collaboration, consultation and instruction between and among heterogeneous networked teams of persons, machines, devices, neural networks, robots and algorithms.

Abstract: A portable communication device supporting video calls is provided. The portable communication device can be configured to perform a video call on the basis of a first video codec and a first audio codec, receive, through a touch display, a request for recording the video call, and, if the first audio codec is not supported by a designated media container, record the video call on the basis of the first video codec and a second audio codec supported by the media container.

Abstract: Methods and systems provide for providing a virtual background within a communication session using dynamic chroma key reframing. In one embodiment, a method displays a user interface including at least one video feed corresponding to a participant of the communication session. The method receives a request to enable a selected or provided virtual background using chroma keying. The method then determines a background layer of the video feed. The method also determines edges for the background layer. Next, the method crops and reframes the video feed around the edges of the background layer. The method then removes the background layer from the video feed, and adds the selected or provided virtual background to the background layer of the video feed. Finally, the method displays the video feed within the communication session.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to determine audio quality. Example apparatus disclosed herein include an equalization (EQ) model query generator to generate a query to a neural network, the query including a representation of a sample of an audio signal. Example apparatus disclosed herein also include an EQ analyzer to access a plurality of equalization settings determined by the neural network based on the query; and compare the equalization settings to an equalization threshold to determine if the audio signal is to be removed from subsequent processing.

Abstract: A headset comprises an ear cup, at least one speaker, an adjustable ear cup shaper, and circuitry. The ear cup shaper is adjustable into at least two configurations, wherein a first of the configurations creates no depression or a first amount of depression in the ear cup and a second of the configurations creates a second amount of depression in the ear cup, where the second amount is greater than the first amount. The circuitry is operable to determine which one of the configurations the ear cup shaper is configured into, and set an audio setting applied to an audio signal output to the speaker based on the determined one of the configurations.

Abstract: Each remote operation terminal includes an own robot sound pressure information transmission unit, an own robot sound pressure information reception unit, an another terminal sound pressure information transmission unit, an another terminal sound pressure information reception unit, a sound pressure information output unit configured to output sound pressure information received by the own robot sound pressure information reception unit or the other terminal sound pressure information reception unit, and a conversation control unit configured to execute an inter-robot conversation mode that establishes conversation with another user using the own robot sound pressure information transmission unit and the own robot sound pressure information reception unit and an inter-terminal conversation mode that establishes conversation with another user using the other terminal sound pressure information transmission unit and the other terminal sound pressure information reception unit in such a way that they can be swit

Abstract: An electronic monitoring system has one or more imaging devices that can detect at least one triggering event comprising sound and motion and a controller that executes a program to categorize the triggering event as being located in a user-defined activity zone within the field of view and/or as being a taxonomic-based triggering event. Upon categorizing the triggering event, the system generates an output comprising a video component and an audio component. At least a portion of the audio component is modified if the triggering event is a categorized triggering event. Modification of the audio may include muting all or a portion of the audio component of the output.

Abstract: Intercom systems and methods for image data transmission are provided. The intercom system may include a first intercom including a first image acquisition device, one or more second image acquisition devices, and a second intercom. During an intercom with the second intercom, the first intercom may receive a request for target image data captured by one or more target image acquisition devices of the first image acquisition device and the one or more second image acquisition devices from the second intercom. The one or more target image acquisition devices may include at least one target second image acquisition device of the one or more second image acquisition devices. In response to the request, the first intercom may obtain the target image data from the one or more target image acquisition devices. The first intercom may also send a signal encoding the target image data to the second intercom for display.

Abstract: An apparatus for analyzing audio includes a feature acquirer, an output apparatus, at least one memory, and at least one processor. The at least one processor is configured to execute a program stored in the at least one memory. The at least one processor is also configured to cause the feature acquirer to acquire a series of feature amounts of an audio signal. The at least one processor is also configured to generate boundary data by inputting the acquired series of feature amounts into a boundary estimation model that has learned relationships between: (i) a series of feature amounts, and (ii) boundary data representative of boundaries, each of the boundaries being between consecutive periods in each of which a chord is continuous.

Abstract: Methods and computer-readable media for repeated holdout validation include collecting independent data representing independent variables; collecting dependent data representing a dependent variable; correlating the independent data with the dependent data; creating a data set comprising the correlated independent and dependent data; generating a plurality of unique seeds; creating a plurality of training sets and a plurality of validation sets; associating each training set with a single validation set; training the neural network a plurality of times with the training sets and seeds to create a plurality of models; calculating accuracy metric values for the models using the validation sets associated with the training sets used to create respective models; performing a statistical analysis of the accuracy metric values; and ranking the independent variables by a strength of correlation of individual independent variables with the dependent variable, when a metric of the statistical analysis exceeds a thres

Abstract: An electronic device includes a processor, and a memory containing instructions that, when executed by the processor, cause the electronic device to learn a sound emitted by a legacy device and to issue an output when the electronic device subsequently hears the sound. For example, the electronic device can receive a training input and extract a compact representation of a sound in the training input, which the device stores. The device can receive an audio signal corresponding to an observed acoustic scene and extract a representation of the observed acoustic scene from the audio signal. The electronic device can determine whether the sound is present in the observed acoustic scene at least in part from a comparison of the representation of the observed acoustic scene with the representation of the sound. The electronic device emits a selected output responsive to determining that the sound is present in the acoustic scene.

Abstract: An electronic device comprises: a housing comprising a front plate, a rear plate facing in the opposite direction to the front plate, and a side member surrounding a space between the front plate and the rear plate; a display which is viewed from the outside through the front plate; a first opening formed between an edge of the front plate and the side member; a mid-plate which is arranged between the display and the rear plate and extends from the side member, overlaps the display when viewed from above the display, and includes a second opening adjacent to the first opening; a speaker which is located in a space adjacent to the second opening, between the mid-plate and the rear plate, and includes a diaphragm facing the display; a sound guide structure arranged between the mid-plate and the display, the sound guide structure comprising a grill portion, which is inserted into the first opening and includes a plurality of through holes, and a flange portion which extends from the grill portion to a space betw

Abstract: System and method for providing fill light on a display of an Information Handling System (IHS) are described. In some embodiments, the IHS may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution by the processor, cause the IHS to: generate, using a camera configured on a display of an Information Handling System (IHS), a first video feed signal of a user positioned in front of the display, and generate an image on the display, the image comprising a first region and a second region, the first region configured to display a second video feed signal from the IHS, the second region configured to generate fill light for enhancing a luminescence of the user.

Abstract: A video call method includes: receiving a first input performed by a user on a first target contact that is displayed on a first screen; and in response to the first input, initiating a video call request to the first target contact, and displaying a video call interface corresponding to the first target contact on the second screen.

Abstract: A vehicle sound service system and a method thereof are provided. The vehicle sound service system includes a service server including a communication device that may be configured to transmit and receive data with a mobile terminal loaded with a camera and a processing device electrically connected with the communication device. The processing device may be configured to receive an image transmitted from the mobile terminal using the communication device, when the mobile terminal captures the image around a vehicle using the camera and transmits the image, to analyze the received image to estimate a driving place, and to select a sound that matches the estimated driving place and transmits the selected sound to the mobile terminal.

Abstract: A display device and a video communication data processing method are disclosed. The method comprises: in response to an instruction for video communication with at least one peer device, a controller collecting a global image of a local device by means of an image acquisition device; and presenting a local preview window in a user interface, and displaying, in the local preview window, a video image of the local device according to the global image, wherein when there is a moving target in the global image, the video image of the local device is a partial image corresponding to a target stable area of the moving target.

Abstract: A system is provided that supports a remote proxy service in which, on behalf of a request source user, a request destination user goes to a location (local site) where the request source user cannot go, and performs what is instructed by the request source user. The system includes a first terminal apparatus used by the request source user and a second terminal apparatus used by the request destination user. The first terminal apparatus displays a moving image captured at a local site by the second terminal apparatus in real time. When the request source user selects an image included in the moving image displayed by the first terminal apparatus, the selected image is displayed on the second terminal apparatus. The request destination user can receive an instruction regarding the object appearing in the image while viewing the image selected by the request source user.

Abstract: An electrical current generating device having a sound wave force magnifying structure in the form of a force transmission pin which is longitudinally slidable within a body bore and having a proximal end of a large area for receiving sound wave forces, and having a greatly reduced area distal end which bears on a piezoelectric element.

Abstract: In one example embodiment, a user conducting an activity is monitored by capturing information of the user and a surrounding environment via one or more sensing devices. The captured information includes images. The captured information is analyzed by a computing device, and one or more interruptions to the user during the activity by one or more entities in the surrounding environment are identified. The identified one or more interruptions to the user are presented on a user interface after completion of the activity.

Abstract: A system and a method for processing a plurality of images, each image of the plurality of images being acquired by a respective image acquisition module of a vehicle and each image acquisition module being oriented outwardly with respect to the vehicle, the method comprising: elaborating a bird's eye view image of surroundings of the vehicle using pixel values of pixels of at least one portion of each image of the plurality of images as pixel values of the bird's eye view image, and performing, on the bird's eye view image, a detection of at least one lane marked on a surface on which the vehicle is and visible on the bird's eye view image.