Abstract: The subject disclosure is directed towards using timing and/or relative depth data to reduce false positives in gesture detection within a depth-sensed region. Depth camera data is processed to position a cursor over a displayed representation of a control. If the user's hand hovers over the control for a threshold time period, and then changes hand depth a relative amount (e.g., pushes the hand forward a delta amount), an event is fired. The displayed representation of the control may change (e.g., enlarge) upon hovering. The relative depth may be computed based upon the depth when the user hand initially enters the control area. The relative depth may remain the same if the user pulls the hand away from the camera by tracking the maximum depth and firing the event when the maximum depth value minus the current depth value reaches a delta value.

Abstract: The subject disclosure is directed towards a noise adaptive beamformer that dynamically selects between microphone array channels, based upon noise energy floor levels that are measured when no actual signal (e.g., no speech) is present. When speech (or a similar desired signal) is detected, the beamformer selects which microphone signal to use in signal processing, e.g., corresponding to the lowest noise channel. Multiple channels may be selected, with their signals combined. The beamformer transitions back to the noise measurement phase when the actual signal is no longer detected, so that the beamformer dynamically adapts as noise levels change, including on a per-microphone basis, to account for microphone hardware differences, changing noise sources, and individual microphone deterioration.

Abstract: The subject disclosure is directed towards using timing and/or relative depth data to reduce false positives in gesture detection within a depth-sensed region. Depth camera data is processed to position a cursor over a displayed representation of a control. If the user's hand hovers over the control for a threshold time period, and then changes hand depth a relative amount (e.g., pushes the hand forward a delta amount), an event is fired. The displayed representation of the control may change (e.g., enlarge) upon hovering. The relative depth may be computed based upon the depth when the user hand initially enters the control area. The relative depth may remain the same if the user pulls the hand away from the camera by tracking the maximum depth and firing the event when the maximum depth value minus the current depth value reaches a delta value.

Abstract: The subject disclosure is directed towards a noise adaptive beamformer that dynamically selects between microphone array channels, based upon noise energy floor levels that are measured when no actual signal (e.g., no speech) is present. When speech (or a similar desired signal) is detected, the beamformer selects which microphone signal to use in signal processing, e.g., corresponding to the lowest noise channel. Multiple channels may be selected, with their signals combined. The beamformer transitions back to the noise measurement phase when the actual signal is no longer detected, so that the beamformer dynamically adapts as noise levels change, including on a per-microphone basis, to account for microphone hardware differences, changing noise sources, and individual microphone deterioration.