Abstract: Aspects of the present disclosure provide methods and apparatuses for determining a subject's sleep stage based on a PPG signal measured using an in-ear earpiece. In aspects, one or more physiological signals are estimated based on the PPG. Based, at least in part, on the determined sleep stage, one or more outputs are provided. In an example, the outputs are provided to the subject, the subject's physician, the subject's clinician, the cloud, and/or a device external to the apparatus. The methods and apparatus of determining the subject's sleep state described herein are continuous and non-invasive and eliminate the need for a clinical setting.

Abstract: The technology described in this document can be embodied in a computer-implemented method that includes receiving information representing audio captured by a microphone array, wherein the information includes multiple datasets each representing audio signals captured in accordance with a sensitivity pattern along a corresponding direction with respect to the microphone array. The method also includes computing, using one or more processing devices for each of the multiple datasets, one or more quantities indicative of human voice activity captured from the corresponding direction, and generating, based at least on the one or more quantities computed for a plurality of the multiple datasets, a directional audio signal representing audio captured from a particular direction.

Abstract: The technology described in this document can be embodied in a computer-implemented method that includes receiving information representing audio captured by a microphone array, wherein the information includes multiple datasets each representing audio signals captured in accordance with a sensitivity pattern along a corresponding direction with respect to the microphone array. The method also includes computing, using one or more processing devices for each of the multiple datasets, one or more quantities indicative of human voice activity captured from the corresponding direction, and generating, based at least on the one or more quantities computed for a plurality of the multiple datasets, a directional audio signal representing audio captured from a particular direction.