Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to dynamically determine interaction display regions for screen sharing. Example apparatus disclosed herein are to generate a screen share frame corresponding to content rendered on the display and intended for the screen share event; identify application-related contextual data corresponding to the screen share event; determine an interactive context based on at least one of (a) the application-related contextual data and (b) sensor data from at least one sensor, the interactive context including identification of an interaction region of the screen share frame; generate interaction metadata that includes the interactive context; and transmit a transport stream that includes the interaction metadata and the screen share frame.

Abstract: Systems and methods to edit videos having voice commands are disclosed herein. An example video editing system includes memory, machine readable instructions, processor circuitry to at least one of instantiate or execute the machine readable instructions to: detect an audible command in audio data, the audible command to control at least one of a function, an operation, a setting, or a state of a controllable device, edit the audio data to remove the audible command, and cause a file including video data and the audio data to be saved.

Abstract: Techniques for teleconferencing with enhanced audio during low-quality connection conditions are disclosed. In the illustrative embodiment, a user of a compute device is teleconferencing with users of one or more remote compute devices. The compute device monitors a connection quality with a remote compute device. If the connection quality drops below a threshold, risking gaps in the audio data, the compute device generates speech code data that can be used to fill in the gaps in the audio data. The remote compute device can use the speech code data to augment the audio data by using a voice model to create additional audio data based on the speech code data.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve screen sharing based on identification of irrelevant video frames from interactive context. Example apparatus disclosed herein are to process input data and application contextual data to determine an interaction classification for a classification interval in a screen sharing event initiated in a video conference and identify, based on the interaction classification, video frames of the screen sharing event that correspond to the classification interval to exclude from a transport stream for the video conference associated with the classification interval. Disclosed example apparatus are further to exclude the identified video frames from the transport stream and provide remaining video frames of the screen sharing event to a video encoder for inclusion in the transport stream.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to designate a display exclusive zone of a display screen. An example computing device to designate a display exclusive zone as disclosed includes at least one memory, instructions in the compute device, and processor circuitry to execute the instructions to designate a portion of a display screen as a display exclusive zone, the display exclusive zone having a first spatial location, the display exclusive zone including first content. The example computing device also includes, in response to receiving a request to render second content, determining a second spatial location of the second content, in response to determining the second spatial location encroaches the first spatial location, adjusting the second spatial location to a third spatial location; and rendering the second content in the third spatial location.

Abstract: Particular embodiments described herein provide for an apparatus to determine biometric data of a user including: a processing circuit configured to: generate a control signal relating to a control value for controlling a wavelength of emitted light of a light source; receive biometric input data based on reflected light from the skin of the user caused by the light of the wavelength emitted by the light source; and determine biometric data of the user based on the biometric input data; and an output interface configured to provide the biometric data of the user.

Abstract: Techniques for ultrasound-based hinge estimation are disclosed. In the illustrative embodiment, a speaker in a base portion of a computing device generates an ultrasonic sound pulse. The pulse is sensed by a microphone in a lid portion of the computing device. The time-of-flight of the sound pulse from the speaker to the microphone is used to determine the distance between the speaker and the microphone.

Abstract: A method for positioning a sensor configured to receive biometric signals includes receiving a biometric signal using a biometric sensor at a first position, the biometric signal comprising a set of raw biometric signal data. In some implementations, signal analysis is used to determine whether at least one signal criteria is met and to determine whether the biometric sensor is moved from the first position to a second position.

Abstract: A method for positioning a sensor configured to receive biometric signals includes receiving a biometric signal using a biometric sensor at a first position, the biometric signal comprising a set of raw biometric signal data. In some implementations, signal analysis is used to determine whether at least one signal criteria is met and to determine whether the biometric sensor is moved from the first position to a second position.

Abstract: Techniques are disclosed for reliably masking speech commands directed to one or more computing devices to prevent the speech commands from being rendered. In some embodiments, each of the one or more computing devices includes components configured to generate acoustic data from ambient sound waves, process the acoustic data to identify a speech command sequence, and mask the speech command sequence from being rendered. At least some of the systems and methods disclosed herein monitor inbound audio at a fine grain level of detail. Working at this level of granularity enables the system and methods described herein to detect potential speech commands early within the user's utterance thereof and to discriminate quickly between true speech commands and other user utterances. These early detection and discrimination features, in turn, enable some embodiments to manage potential communication disruptions (e.g., jitter and/or latency) by modifying rates of audio prior to rendering.

Abstract: Capacitive ECG sensing electronic displays and related methods are disclosed herein. An example electronic device disclosed herein includes a display screen including a first electrode and a second electrode and a processor operatively coupled to the display screen. The processor is to cause the display screen to operate in a first display screen mode to detect a touch input from a user on the display screen. The processor is to cause the display screen to switch from operating in the first display screen mode to operating in a second display screen mode. The first electrode and the second electrode are to generate signal data indicative of electrocardiogram data for the user when the display screen is operating in the second display screen mode.

Abstract: Video overlays are modified to enhance readability. In one example a frame of a video sequence of frames is received and an overlay for display on the frame is received. A location of the overlay in the frame is determined. Background pixels in the frame that are in the overlay location are determined. Values of the identified pixels are analyzed and an overlay color is selected based on the analysis. The overlay is then blended into the frame using the selected overlay color.

Abstract: A text-only transcription of spoken input from one or more speakers is enhanced with context information that indicate the speakers' states, including physical, emotional, and mental conditions. Context information includes information sensed or otherwise gathered from the speakers' surroundings. The contextual information in the resulting enhanced transcription can facilitate a more accurate understanding of the speakers' intended meaning, and thus avoid misunderstandings that can be detrimental to the relationship between speaker and listener and avoid time consuming activity to rectify misunderstandings.

Abstract: Techniques are disclosed for reliably masking speech commands directed to one or more computing devices to prevent the speech commands from being rendered. In some embodiments, each of the one or more computing devices includes components configured to generate acoustic data from ambient sound waves, process the acoustic data to identify a speech command sequence, and mask the speech command sequence from being rendered. At least some of the systems and methods disclosed herein monitor inbound audio at a fine grain level of detail. Working at this level of granularity enables the system and methods described herein to detect potential speech commands early within the user's utterance thereof and to discriminate quickly between true speech commands and other user utterances. These early detection and discrimination features, in turn, enable some embodiments to manage potential communication disruptions (e.g., jitter and/or latency) by modifying rates of audio prior to rendering.

Abstract: Techniques and mechanisms for a first voice assistant to automatically participate in speech communication with a second voice assistant. In an embodiment, circuitry of a first device provides an input and/or output (IO) interface of the first voice assistant, and detects a first utterance spoken by a participant in a conversation. Based on an analysis of the first utterance, the device detects a pendency of a first request of the conversation. A second utterance of the first voice assistant is automatically generated by the device based on the pendency of the first request and a detected availability of the second voice assistant. The second utterance represents a second request which comprises a handle to address the second voice assistant. In another embodiment, the handle is generated automatically based on profile information which describes (or is otherwise associated with) a characteristic of the second voice assistant.

Abstract: Various systems and methods for processing video data, including gesture masking in a video feed, are provided herein. The system can include a camera system interface to receive video data from a camera system; a gesture detection unit to determine a gesture within the video data, the gesture being performed by a user; a permission module to determine a masking permission associated with the gesture; and a video processor. The video processor can modify a portion of the video data associated with the gesture in accordance with the masking permission, and cause the portion of the video data to be displayed. The camera system includes a depth camera or an infrared camera. The gesture detection unit determines the gesture based on machine learning.

Abstract: Various systems and methods for processing video data, including gesture masking in a video feed, are provided herein. The system can include a camera system interface to receive video data from a camera system; a gesture detection unit to determine a gesture within the video data, the gesture being performed by a user; a permission module to determine a masking permission associated with the gesture; and a video processor. The video processor can modify a portion of the video data associated with the gesture in accordance with the masking permission, and cause the portion of the video data to be displayed. The camera system includes a depth camera or an infrared camera. The gesture detection unit determines the gesture based on machine learning.

Abstract: Video overlays are modified to enhance readability. In one example a frame of a video sequence of frames is received and an overlay for display on the frame is received. A location of the overlay in the frame is determined. Background pixels in the frame that are in the overlay location are determined. Values of the identified pixels are analyzed and an overlay color is selected based on the analysis. The overlay is then blended into the frame using the selected overlay color.