Abstract: Various systems, devices, and methods for social interaction measurement that preserve privacy are presented. An audio signal can be captured using a microphone. The audio signal can be processed using an audio-based machine learning model that is trained to detect the presence of speech. The audio signal can be discarded such that content of the audio signal is not stored after the audio signal is processed using the machine learning model. An indication of whether speech is present within the audio signal can be output based at least in part on processing the audio signal using the audio-based machine learning model.

Abstract: Systems, devices, and methods for tracking one or more physiological metrics (e.g., heart rate, blood oxygen saturation, and the like) of a user are described. For example, one or more light sources and one or more light detectors may be positioned on a wearable device such that light can be emitted towards the user's skin and further such that light reflected back to the wearable device can be measured and used to generate values for the one or more physiological metrics.

Abstract: A wearable device includes at least one attachment member and an electrodermal activity (EDA) sensor comprising an integrated electrode pair physically coupled to the at least one attachment member. The electrodermal activity sensor is configured to provide an EDA signal in response to contact between the integrated electrode pair and a skin surface of a user. The integrated electrode pair includes at least two concentric electrodes radially separated by at least one insulator. Each of the at least two concentric electrodes includes an upper surface configured to contact the skin surface of the user in order to generate the EDA signal.