Abstract: Hearing protection and communication apparatus using vibration sensors are disclosed. An example wearable electronic device includes means for transducing vibrations associated with speech into a first signal; means for transducing sound associated with ambient noise into a second signal; and means for processing to cause a speaker to output a signal to reduce the ambient noise; detect an identifier in the speech; and cause audio data representative of the speech to be transmitted to a second device associated with the identifier.

Abstract: Various systems and methods for implementing distribution of a neural network workload are described herein. A discovery message is encoded that includes a latency requirement and requested resources for a workload of a neural network. A discovery response, from a proximate resource and in response to the discovery message, is decoded and includes available resources of the proximate resource available for the workload based on the requested resources for the workload. The proximate resource is selected to execute the workload based on the available resources of the proximate resource. In response to the discovery response, an offload request is encoded that includes a description of the workload. The description of the workload identifies the node to execute at the proximate resource. In response to the offload request, an input is provided to a ADAS system based on the result.

Abstract: Hearing protection and communication apparatus using vibration sensors are disclosed. An example wearable electronic device includes means for transducing vibrations associated with speech into a first signal; means for transducing sound associated with ambient noise into a second signal; and means for processing to cause a speaker to output a signal to reduce the ambient noise; detect an identifier in the speech; and cause audio data representative of the speech to be transmitted to a second device associated with the identifier.

Abstract: An example apparatus for hearing protection and communication includes safety glasses including a vibration sensor to capture speech from a user. The apparatus also includes hearing protectors communicatively coupled to the safety glasses and one or more other devices. The hearing protectors are to reduce a volume of an ambient sound and play back captured speech from the one or more other devices. The apparatus also further includes a number of wireless communication elements to communicatively couple the safety glasses, the hearing protectors, and at least a second apparatus for hearing protection and communication.

Abstract: Methods, apparatus, systems and articles of manufacture for acoustic system noise mitigation are disclosed. An example apparatus includes a sound sensor and one or more electronic components. The apparatus also includes a background noise analyzer to obtain sensor data indicative of background noise in an environment of the apparatus from the sound sensor. The apparatus also includes a system noise analyzer to select a first system noise profile indicative of acoustic noise associated with operating the one or more electronic components according to a first system configuration. The apparatus also includes a system noise controller to operate the one or more electronic components according to the first system configuration of the first system noise profile.

Abstract: Methods, systems, and apparatus for drone collision avoidance and acoustic sensing are disclosed. An example apparatus to detect acoustic data from a drone includes a controller to set a target revolutions per minute (RPM) for a motor of the drone. The controller is to modify the target RPM based on a modulation pattern to cause the motor to rotate a propeller of the drone at a modulated RPM. The modulated RPM creates self-generated noise. The example apparatus also includes a sensor to gather acoustic data and an analyzer to remove the self-generated noise from the acoustic data to create external acoustic data for processing.

Abstract: Systems and methods may include a lift drone and a carrier drone to convey a payload. The lift drone may vertically lift the payload, alone or with the carrier drone, to a transfer location. The carrier drone may receive control of the payload at the transfer location, such as by receiving physical transfer of the payload, taking over conveyance of the payload from the lift drone, or the like. The lift drone may remain coupled with the payload or the carrier drone or may decouple after transfer.

Abstract: An example unmanned aerial vehicle traffic signal and related methods are disclosed. The example unmanned aerial vehicle includes a housing, a rotor, a motor, a sensor, a traffic signal, and a processor. The rotor is to lift the housing off ground. The motor is to drive the rotor. The sensor is to monitor traffic. The traffic signal is carried by the housing. The processor is to control the traffic signal based on the traffic monitored by the sensor.

Abstract: An example apparatus for generating dialogue includes an audio receiver to receive audio data including speech. The apparatus also includes a verification score generator to generate a verification score based on the audio data. The apparatus further includes a user detector to detect that the verification score exceeds a lower threshold but does not exceed a higher threshold. The apparatus includes a dialogue generator to generate dialogue to solicit additional audio data to be used to generate an updated verification score in response to detecting that the verification score exceeds a lower threshold but does not exceed a higher threshold.

Abstract: An example apparatus for detecting speech includes an image receiver to receive depth information corresponding to a face. The apparatus also includes a landmark detector to detect the face comprising lips and track a plurality of descriptor points comprising lip descriptor points located around the lips. The apparatus further includes a descriptor computer to calculate a plurality of descriptor features based on the tracked descriptor points. The apparatus includes a pattern generator to generate a visual pattern of the descriptor features over time. The apparatus also further includes a speech recognition engine to detect speech based on the generated visual pattern.

Abstract: Methods and apparatus relating to characterizing proximity risks within a radio mesh are described. In an embodiment, collection logic receives risk data from one or more source devices and memory stores the risk data. Pattern logic analyzes the stored risk data to determine existence of one or more risks. The risk data includes results of two-way ping signals communicated between the one or more source devices and a target device. Other embodiments are also disclosed and claimed.

Abstract: Systems and methods may include a lift drone and a carrier drone to convey a payload. The lift drone may vertically lift the payload, alone or with the carrier drone, to a transfer location. The carrier drone may receive control of the payload at the transfer location, such as by receiving physical transfer of the payload, taking over conveyance of the payload from the lift drone, or the like. The lift drone may remain coupled with the payload or the carrier drone or may decouple after transfer.

Abstract: Various systems and methods for implementing distribution of a neural network workload are described herein. A discovery message is encoded that includes a latency requirement and requested resources for a workload of a neural network. A discovery response, from a proximate resource and in response to the discovery message, is decoded and includes available resources of the proximate resource available for the workload based on the requested resources for the workload. The proximate resource is selected to execute the workload based on the available resources of the proximate resource. In response to the discovery response, an offload request is encoded that includes a description of the workload. The description of the workload identifies the node to execute at the proximate resource. In response to the offload request, an input is provided to a ADAS system based on the result.

Abstract: Methods and apparatus relating to characterizing proximity risks within a radio mesh are described. In an embodiment, collection logic receives risk data from one or more source devices and memory stores the risk data. Pattern logic analyzes the stored risk data to determine existence of one or more risks. The risk data includes results of two-way ping signals communicated between the one or more source devices and a target device. Other embodiments are also disclosed and claimed.

Abstract: An example apparatus for hearing protection and communication includes safety glasses including a vibration sensor to capture speech from a user. The apparatus also includes hearing protectors communicatively coupled to the safety glasses and one or more other devices. The hearing protectors are to reduce a volume of an ambient sound and play back captured speech from the one or more other devices. The apparatus also further includes a number of wireless communication elements to communicatively couple the safety glasses, the hearing protectors, and at least a second apparatus for hearing protection and communication.

Abstract: Methods, systems, and apparatus for drone collision avoidance and acoustic sensing are disclosed. An example apparatus to detect acoustic data from a drone includes a controller to set a target revolutions per minute (RPM) for a motor of the drone. The controller is to modify the target RPM based on a modulation pattern to cause the motor to rotate a propeller of the drone at a modulated RPM. The modulated RPM creates self-generated noise. The example apparatus also includes a sensor to gather acoustic data and an analyzer to remove the self-generated noise from the acoustic data to create external acoustic data for processing.

Abstract: An example apparatus for generating dialogue includes an audio receiver to receive audio data including speech. The apparatus also includes a verification score generator to generate a verification score based on the audio data. The apparatus further includes a user detector to detect that the verification score exceeds a lower threshold but does not exceed a higher threshold. The apparatus includes a dialogue generator to generate dialogue to solicit additional audio data to be used to generate an updated verification score in response to detecting that the verification score exceeds a lower threshold but does not exceed a higher threshold.

Abstract: Speech from multiple users is distinguished. In one example, an apparatus has a sensor to determine a position of a speaker, a microphone array to receive audio from the speaker and from other simultaneous audio sources, and a processor to select a pre-determined filter based on the determined position and to apply the selected filter to the received audio to separate the audio from the speaker from the audio from the other simultaneous audio sources.

Abstract: An example apparatus for detecting speech includes an image receiver to receive depth information corresponding to a face. The apparatus also includes a landmark detector to detect the face comprising lips and track a plurality of descriptor points comprising lip descriptor points located around the lips. The apparatus further includes a descriptor computer to calculate a plurality of descriptor features based on the tracked descriptor points. The apparatus includes a pattern generator to generate a visual pattern of the descriptor features over time. The apparatus also further includes a speech recognition engine to detect speech based on the generated visual pattern.

Abstract: An example unmanned aerial vehicle traffic signal and related methods are disclosed. The example unmanned aerial vehicle includes a housing, a rotor, a motor, a sensor, a traffic signal, and a processor. The rotor is to lift the housing off ground. The motor is to drive the rotor. The sensor is to monitor traffic. The traffic signal is carried by the housing. The processor is to control the traffic signal based on the traffic monitored by the sensor.