Abstract: A system is described herein. The system includes at least one hardware processor that is configured to identify a pre-determined acoustic barrier filter, wherein the acoustic barrier filter coincides with the physical acoustic barrier and receive an audio signal within a time window at the first microphone and the second microphone. The hardware processor is also configured to calculate a first measure of variability, a second measure of variability, a third measure of variability, and a fourth measure of variability. The hardware processor further concatenates the first measure of variability, the second measure of variability, the third measure of variability, and the fourth measure of variability to form a feature vector, and inputs the feature vector into a location classifier to obtain an audio source location.

Abstract: Systems, apparatuses and methods may provide for technology that adjusts a plurality of weights in a neural network model and adjusts a plurality of activation functions in the neural network model. The technology may also output the neural network model in response to one or more conditions being satisfied by the plurality of weights and the plurality of activation functions. In one example, two or more of the activation functions are different from one another and the activation functions are adjusted on a per neuron basis.

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: Technology for a mobile device is described. The mobile device can include a vibration motor operable to generate a vibration, and a sensor operable to capture a plurality of vibration signals that result from the vibration. The mobile device can provide the plurality of vibration signals to a model running on the mobile device. The model can include a plurality of predefined patterns that correspond to vibration signals produced by mobile devices residing on different surfaces. The mobile device can identify, using the model, a predefined pattern in the plurality of predefined patterns that substantially corresponds to the plurality of vibration signals based on a confidence level that exceeds a threshold. The mobile device can determine a type of surface on which the mobile device resides based on the predefined pattern identified using the model.

Abstract: In some embodiments, a method calculates a first color metric value from a detection window in a first image that is detected by a visual system. A second image of pixels is generated where the pixels include one or more second color metric values that meet the first color metric value within a threshold. The method compares the second image to an object. When the comparison meets a criterion, the method transitions from a first mode to a second mode. When the comparison does not meet the criterion, the method continues to operate in the first mode.

Abstract: Methods, systems, and apparatus for audio noise reduction from a drone are disclosed. An example apparatus includes an acoustic sensor to gather acoustic data and at least one rotational motion sensor to gather rotational motion data of a first rotor and second rotational motion data of a second rotor. The example apparatus also includes an analyzer to identify a first filter that matches the first rotational motion data and identify a second filter that matches the second rotational motion data. The analyzer also is to filter the acoustic data into filtered acoustic data with the first identified filter and the second identified filter and generate an audio signal based on the filtered acoustic data.

Abstract: A system, article, and method of acoustic angle of arrival detection uses both same-time and delayed-time audio signal value comparisons in a time domain that are input to a classifier neural network.

Abstract: A wearable gesture recognition device is disclosed that provides gesture recognition for gestures that may include a hold or steady-state component, and may account and adapt for real-time fit-level changes. The wearable gesture recognition device may integrate a photoplethysmographic (PPMG) and a piezoelectric (PZE) sensor such that respective sensor signals may be used individually, or in concert for gesture recognition. Thus the wearable gesture recognition device generally disclosed herein may advantageously perform gesture recognition through the fusion of PPMG and PZE signals. To support continuous gesture recognition, the wearable gesture recognition device may use a low-power activity detection scheme that analyzes a PZE signal prior to higher-power gesture classification. Moreover, the wearable gesture recognition device may provide power management by controlling a duty-cycle of the PPMG sensor without necessarily reducing recognition performance.

Abstract: Embodiments of the present disclosure provide techniques and configurations for an apparatus for detection of a change of electromagnetic field in response to a gesture, to identify the gesture that caused the field change. In one instance, the apparatus may include a first conducting component having first features for the disposal on or around a portion of a user's body, to generate an electromagnetic field in response to a receipt of a source signal. The apparatus may further include a second conducting component having second features for the disposal on or around a portion of the user's body, at a distance from the first conducting component, to provide an indication of a change in the electromagnetic field over time, to identify a change of a position of the user's body portion (gesture) that causes the change in the electromagnetic field. Other embodiments may be described and/or claimed.

Abstract: Embodiments of the present disclosure provide techniques and configurations for an apparatus for a user's physiological context measurements. In one instance, the apparatus may include a processing block and first and second piezoelectric sensors coupled with the processing block. The first and second sensors may include respectively first and second electrodes to provide contact with a user's body in response to mounting of the apparatus on the user's body. The processing block may comprise a multi-modal sensing system configured to perform measurements of a user's physiological context during the contact of the user's body with the first and second electrodes, based at least in part on a voltage signal generated by the user's body and provided to the processing block via the first and second electrodes. Other embodiments may be described and/or claimed.

Abstract: Methods, systems, and apparatus for audio noise reduction from a drone are disclosed. An example apparatus includes a first sensor to gather acoustic data and a second sensor to gather rotational motion data of a rotor. The example apparatus also includes an analyzer to match the rotational motion data to a filter and filter the acoustic data using the filter. The analyzer also is to generate an audio signal based on the filtered acoustic data.

Abstract: The apparatus includes an apparatus for harvesting energy. The apparatus includes a textile having an insulating substrate, a direct current (DC) power bus structure disposed in the insulating substrate, and multiple transducers. The DC power bus includes a positive conductor and a ground conductor. The transducers are secured to the insulating substrate and in electrical contact with the positive conductor and the ground conductor. Additionally, the DC bus remains conductively coupled to the transducers remaining in the textile after the textile is cut.

Abstract: Embodiments of the present disclosure provide techniques and configurations for an apparatus to determine a command to the apparatus, based on vibration patterns. In one instance, the apparatus may include a body with at least one surface to receive one or more user inputs; at least one sensor disposed to be in contact with the body to detect vibration manifested by the surface in response to the user input, and generate a signal indicative of vibration detected; and a controller coupled with the sensor, to process the vibration-indicative signal, to identify a vibration pattern, and determine a command based at least in part on the vibration pattern, based at least in part on a result of the process of the signal. The command may be provided to interact, operate, or control the apparatus. Other embodiments may be described and/or claimed.

Abstract: Systems, apparatuses and methods for secure audio acquisition. The method includes receiving audio data via a digital microphone. The digital microphone outputs a single bit at a high sampling rate. The digital microphone output is converted to a full range audio signal. The full range audio signal is filtered to provide a band limited audio output that avoids capture of enough of a spectral range of speech for the speech to be intelligible.

Abstract: Embodiments of the present disclosure provide techniques and configurations for an apparatus for a user's physiological context measurements. In one instance, the apparatus may include a head-fitting component to be mounted at least partly around a user's head, and a sensor disposed on the head-fitting component to generate a signal indicative of a user's physiological context in response to contact with the user's head. The physiological context may comprise a respiration cycle, and the sensor may sense vibration in a portion of the user's head produced in response to the respiration cycle. The apparatus may further include a controller coupled with the sensor, to process the signal and generate data indicative of the physiological context of the user. Other embodiments may be described and/or claimed.

Abstract: Methods, systems, and apparatus for audio noise reduction from a drone are disclosed. An example apparatus includes a first sensor to gather acoustic data and a second sensor to gather rotational motion data of a rotor. The example apparatus also includes an analyzer to match the rotational motion data to a filter and filter the acoustic data using the filter. The analyzer also is to generate an audio signal based on the filtered acoustic data.

Abstract: Methods and apparatuses for implementing a neural network using symmetric tensors. In embodiments, a system may include a higher order neural network with a plurality of layers that includes an input layer, one or more hidden layers, and an output layer. Each of the input layer, the one or more hidden layers, and the output layer includes a plurality of neurons, where the plurality of neurons includes at least first order neurons and second order neurons, and where inputs at a second order neuron are combined using a symmetric tensor.

Abstract: Methods and apparatuses for identifying food chewed or beverage drank are disclosed herein. In embodiments, a device may comprise one or more sensors to provide vibration signal data representative of vibrations sensed from a nasal bridge of a user wearing the device, a chewing analyzer to extract from the vibration signal data a first plurality of features associated with chewing activities, and/or a drinking analyzer is to extract from the vibration signal data a second plurality of features associated with drinking activities. The extracted first and/or second plurality of features, in turn, may be used to determine a category of food the user was chewing, or a category of beverage the user was drinking. In embodiments, the methods and apparatuses may use personalized models.

Abstract: Apparatuses and methods for transforming a signal from a vibration sensor into an approximation of a signal from a microphone are disclosed. The vibration sensor signal may be transformed by first obtaining a smooth average spectrum and corresponding deviation data for the vibration sensor signal. The smooth average spectrum may be passed through a mapping neural network to obtain a transformed smooth average spectrum that approximates a smooth average spectrum that would be obtained from a microphone. The transformed signal is then obtained by recombining the transformed smooth average spectrum with the deviation data.

Abstract: Methods and apparatus for identifying breathing patterns are disclosed herein. An example wearable device includes a sensor positioned to generate vibration signal data from a nasal bridge of a user, a breathing phase detector to identify a first and second breathing phases based on the vibration signal data, a phase timing calculator to calculate a first time period for the first breathing phase and a second time period for the second breathing phase, a breathing pattern detector to generate a breathing pattern metric based on the first and second time periods, a breathing activity detector to identify a breathing activity associated with the vibration signal data based on the breathing pattern metric, and an alert generator to activate an output device to generate at least one of an audible, tactile, or visual alert based on at least one of the breathing activity and a change associated with the breathing activity.