Abstract: Far field devices typically rely on audio only for enabling user interaction and involve only audio processing. Adding a vision-based modality can greatly improve the user interface of far field devices to make them more natural to the user. For instance, users can look at the device to interact with it rather than having to repeatedly utter a wakeword. Vision can also be used to assist audio processing, such as to improve the beamformer. For instance, vision can be used for direction of arrival estimation. Combining vision and audio can greatly enhance the user interface and performance of far field devices.

Abstract: Detection points may be first observed over multiple radar frames. The observed detection points, which form the tracklets, can be used to form a segmentation of the present radar frame by associating the tracklats to at least one object-track, which represents at least one object based on at least one feature-parameter. Segmentation results from tracking of detection points over multiple radar frames (viz. utilizing tracking information) which is used for associating detection points to objects (segmentation-by-tracking). A two-level tracking approach can be implemented, in which for a present radar frame, (new) detection points are associated to tracklets, which may be seen as a first level, and then the tracklets are associated to object-tracks, which may be seen as a second level.

Abstract: Far field devices typically rely on audio only for enabling user interaction and involve only audio processing. Adding a vision-based modality can greatly improve the user interface of far field devices to make them more natural to the user. For instance, users can look at the device to interact with it rather than having to repeatedly utter a wakeword. Vision can also be used to assist audio processing, such as to improve the beamformer. For instance, vision can be used for direction of arrival estimation. Combining vision and audio can greatly enhance the user interface and performance of far field devices.

Abstract: A signal acquisition system configured to track a physiologic signal of a person includes a first accelerometer having a first accelerometer channel configured to obtain information of a physiologic signal. The physiologic signal is obtained extracorporeally. A control circuit receives data from the first accelerometer channel to identify, using at least one harmonic template, a base frequency of the physiologic signal. The system applies a filter to establish a tracking signal initialized with the identified base frequency and stores and/or transmits the tracking signal as a representation of the physiologic signal. The system alternatively performs filtration and estimation operations to extract physiologic information including heart rate, heart rate variability, and respiration rate from the physiologic signal.

Abstract: The battery monitoring techniques described herein may be used for detection of battery anomalies or faults. Also, the battery monitoring techniques described herein may be used to generate estimates of total battery capacity. The battery monitoring techniques may employ an alternating current frequency response (ACFR) of the battery. The ACFR response of the battery may be used to detect anomalies and/or estimate a total capacity of the battery.

Abstract: A method collects radar signals reflected from particles distributed by an emission device. A three-dimensional range-angle-velocity cube is formed from the radar signals. The three-dimensional range-angle-velocity cube includes individual bins with radar intensity values characterizing angle and range for a specific velocity. The three-dimensional range-angle-velocity cube is analyzed to identify a ground plane and radar signals reflected from particles immediately proximate to the ground plane. Total particle deposition distribution is predicted.

Abstract: A device for proximity detection includes multiple electrodes and an impedance sensor coupled to the electrodes. The impedance sensor may include three impedance elements and a sensing element arranged in a bridge configuration to offset an external impedance and detect changes to impedance in the environment of the device. The device further includes a proximity detector that obtains sensor measurements between multiple subsets of electrodes and analyzes the sensor measurements to determine whether an object is approaching the device.

Abstract: A method includes an operation to collect radar signals reflected from objects in a field of view. Range-angle-doppler bins representing three-dimensional objects in the field of view are formed. A local median operation is used across a selected dimension of the range-angle-doppler bins to eliminate background noise in the range-angle-doppler bins. Low energy peak regions are masked by removing radial velocity values in the selected dimension to form a sparse range-angle two-dimensional grid. The radar signals reflected from objects in the view of view are processed to extract reflection point detections. Reflection point detections are tracked in accordance with short-term filter rules to form tracked reflection point detections. The tracked reflection point detections are formed into clusters. The clusters are processed with long-term filter rules.

Abstract: The battery monitoring techniques described herein may be used for detection of battery anomalies or faults. Also, the battery monitoring techniques described herein may be used to generate estimates of total battery capacity. The battery monitoring techniques may employ an alternating current frequency response (ACFR) of the battery. The ACFR response of the battery may be used to detect anomalies and/or estimate a total capacity of the battery.

Abstract: Far field devices typically rely on audio only for enabling user interaction and involve only audio processing. Adding a vision-based modality can greatly improve the user interface of far field devices to make them more natural to the user. For instance, users can look at the device to interact with it rather than having to repeatedly utter a wakeword. Vision can also be used to assist audio processing, such as to improve the beamformer. For instance, vision can be used for direction of arrival estimation. Combining vision and audio can greatly enhance the user interface and performance of far field devices.

Abstract: An approach to processing of acoustic signals acquired at a user's device include one or both of acquisition of parallel signals from a set of closely spaced microphones, and use of a multi-tier computing approach in which some processing is performed at the user's device and further processing is performed at one or more server computers in communication with the user's device. The acquired signals are processed using time versus frequency estimates of both energy content as well as direction of arrival. In some examples, a non-negative matrix or tensor factorization approach is used to identify multiple sources each associated with a corresponding direction of arrival of a signal from that source. In some examples, data characterizing direction of arrival information is passed from the user's device to a server computer where direction-based processing is performed.

Abstract: An approach to separating multiple sources exploits the observation that each source is associated with a linear-circular phase characteristic in which the relative phase between pairs of microphones follows a linear (modulo) pattern. In some examples, a modified RANSAC (Random Sample Consensus) approach is used to identify the frequency/phase samples that are attributed to each source. In some examples, either in combination with the modified RANSAC approach or using other approaches, a wrapped variable representation is used to represent a probability density of phase, thereby avoiding a need to “unwrap” phase in applying probabilistic techniques to estimating delay between sources.

Abstract: An approach to processing of acoustic signals acquired at a user's device include one or both of acquisition of parallel signals from a set of closely spaced microphones, and use of a multi-tier computing approach in which some processing is performed at the user's device and further processing is performed at one or more server computers in communication with the user's device. The acquired signals are processed using time versus frequency estimates of both energy content as well as direction of arrival. In some examples, a non-negative matrix or tensor factorization approach is used to identify multiple sources each associated with a corresponding direction of arrival of a signal from that source. In some examples, data characterizing direction of arrival information is passed from the user's device to a server computer where direction-based processing is performed.