Abstract: A welding assembly is disclosed. The welding assembly includes a plurality of separately controllable actuators (e.g., pneumatic, having an axially movable ram) to press a corresponding portion of a first workpiece (e.g., a discrete flange of a first stiffener) against a second workpiece (e.g., an outer skin) for welding operations (e.g., via induction welding).

Abstract: System and techniques for tracking caloric expenditure using sensor driven fingerprints are described herein. A set of outputs may be obtained from a plurality of sensors. A fingerprint may be generated using the set of outputs. The fingerprint may correspond to an activity observed by the plurality of sensors. The generated fingerprint may be compared to a set of fingerprints stored in a database. Each fingerprint of the set of fingerprints may correspond to a respective caloric expenditure. A caloric expenditure may be calculated for the activity based on the comparison. An exercise profile of a user may be updated using the caloric expenditure.

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: An apparatus of a multiagent system comprises a processing unit to process a unit of analysis on sensor data received from a sensor, and to provide a latency estimate to process the unit of analysis, and a decision system coupled with the processing unit to execute a decision process in response to an event, wherein the decision system utilizes the latency estimate as part of the decision process.

Abstract: In an embodiment, a system includes a wearable device having a sensor that detects whisper data from a user. The whisper data may include vibrational data, audio data, and/or biometric signals, and correspond to words whispered by the user at a first decibel level. The system also includes a processor communicatively coupled to the sensor that extracts features associated with the whisper data including frequencies and/or amplitudes associated with the whispered data, and generates speech data based on the whisper data and the features. The speech data corresponds to the words spoken at a second decibel level, where the second decibel level is greater than the first decibel level.

Abstract: Techniques related to a method and system of robust speaker recognition activation are described herein. Such techniques apply keyphrase detection and speaker recognition to a subsequent phrase after detecting a waking keyphrase.

Abstract: A convolutional neural network for classifying time series data uses a dynamic context selection. In one example a method includes receiving a plurality of inputs of different sizes at a convolutional neural network, applying convolution and pooling to each of the inputs to provide a plurality of outputs of different sizes, changing the size of each of the outputs to a selected uniform size, reshaping each of the outputs to a vector, and fully connecting the vectors.

Abstract: Techniques related to speaker recognition are discussed. Such techniques include determining context aware confidence values formed of false accept and false reject rates determined by using adaptively updated acoustic environment score distributions matched to current score distributions.

Abstract: A method is provided. The method includes receiving inputs typed by a user of a keyboard and analyzing the inputs to identify typing errors made by the user. The method also includes customizing a layout of the keyboard to reduce the identified typing errors.

Abstract: Technologies for automated context-aware media curation include a computing device that captures context data associated with media objects. The context data may include location data, proximity data, behavior data of the user, and social activity data. The computing device generates inferred context data using one or more cognitive or machine learning algorithms. The inferred context data may include semantic time or location data, activity data, or sentiment data. The computing device updates a user context model and an expanded media object graph based on the context data and the inferred context data. The computing device selects one or more target media objects using the user context model and the expanded media object graph. The computing device may present context-aware media experiences to the user with the target media objects. Context-aware media experiences may include contextual semantic search and contextual media browsing. Other embodiments are described and claimed.

Abstract: In some embodiments, the disclosed subject matter involves identifying environmental factors and user context that affect sleep quality. Embodiments use information about the static sleep environment, as well as dynamic environmental factors, such as sound, light, movement, correlated with user context, such as physical and emotional state, as well, as recent behavior to classify sleep data. The correlated and classified sleep data may be used to provide change recommendations, where implementing the recommended change is believed to improve the user's sleep quality. Other embodiments are described and claimed.

Abstract: Techniques are provided for training of a text independent (TI) speaker recognition (SR) model. A methodology implementing the techniques according to an embodiment includes measuring context data associated with collected TI speech utterances from a user and identifying the user based on received identity measurements. The method further includes performing a speech quality analysis and a speaker state analysis based on the utterances, and evaluating a training merit value of the utterances, based on the speech quality analysis and the speaker state analysis. If the training merit value exceeds a threshold value, the utterances are stored as training data in a training database. The database is indexed by the user identity and the context data. The method further includes determining whether the stored training data has achieved a sufficiency level for enrollment of a TI SR model, and training the TI SR model for the identified user and context.

Abstract: A portable electronic device may generate a (RF) radio frequency fingerprint that includes information representative of at least a portion of RF signals received at a given physical location. The RF fingerprint may include, for example, a unique identifier and a signal strength that are both logically associated with at least a portion of the received RF signals. The portable electronic device may also receive data representative of a number of environmental parameters about the portable electronic device. These environmental parameters may be measured using sensors carried by the portable electronic device. Considered in combination, these environmental parameters provide an environmental signature for a given location. When combined into a data cluster, the RF fingerprint and the environmental signature may provide an indication of the physical subdivision where the portable electronic device is located.

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: An apparatus of a multiagent system comprises a processing unit to process a unit of analysis on sensor data received from a sensor, and to provide a latency estimate to process the unit of analysis, and a decision system coupled with the processing unit to execute a decision process in response to an event, wherein the decision system utilizes the latency estimate as part of the decision process.

Abstract: Techniques related to a method and system of robust speaker recognition activation are described herein. Such techniques apply keyphrase detection and speaker recognition to a subsequent phrase after detecting a waking keyphrase.

Abstract: Techniques are provided for training of a text independent (TI) speaker recognition (SR) model. A methodology implementing the techniques according to an embodiment includes measuring context data associated with collected TI speech utterances from a user and identifying the user based on received identity measurements. The method further includes performing a speech quality analysis and a speaker state analysis based on the utterances, and evaluating a training merit value of the utterances, based on the speech quality analysis and the speaker state analysis. If the training merit value exceeds a threshold value, the utterances are stored as training data in a training database. The database is indexed by the user identity and the context data. The method further includes determining whether the stored training data has achieved a sufficiency level for enrollment of a TI SR model, and training the TI SR model for the identified user and context.

Abstract: Techniques related to speaker recognition are discussed. Such techniques include determining context aware confidence values formed of false accept and false reject rates determined by using adaptively updated acoustic environment score distributions matched to current score distributions.

Abstract: In some embodiments, the disclosed subject matter involves identifying environmental factors and user context that affect sleep quality. Embodiments use information about the static sleep environment, as well as dynamic environmental factors, such as sound, light, movement, correlated with user context, such as physical and emotional state, as well, as recent behavior to classify sleep data. The correlated and classified sleep data may be used to provide change recommendations, where implementing the recommended change is believed to improve the user's sleep quality. Other embodiments are described and claimed.

Abstract: In some embodiments, the disclosed subject matter involves a system and method relating to improving the user experience of hearing, using an adaptable or adjustable hearing aid that takes environmental conditions into account when changing modes. A local server or gateway or cloud service iteratively analyzes the audio environment and feedback from the user to automatically change settings and mode of the user's hearing aid to improve hearing. Information from other users in similar audio environments may be used to assist in mode changes. Information about the audio environment, hearing aid settings/mode and user feedback may be correlated for future use by the user, or crowdsourced for other users, the hearing aid manufacturer or audiologist. Other embodiments are described and claimed.