Audio-based gesture detection

摘要

An audio device may be configured to detect proximity of a user hand based on analysis of audio signals captured by the audio device. For example, the audio device may be configured to perform acoustic echo cancellation based on dynamically calculated filter coefficients. The coefficients may be analyzed to determine proximity of the user hand. The proximity of the hand may be evaluated over time to detect user hand gestures.

主权项

1. An audio device, comprising:
a speaker configured to generate output audio based at least in part on an output audio signal; a microphone configured to produce an input audio signal, wherein the input audio signal contains one or more acoustic echoes of the output audio; an acoustic echo cancellation element configured to:
receive the input audio signal;dynamically update a sequence of acoustic echo cancellation (AEC) coefficients to estimate the one or more acoustic echoes of the output audio, wherein a first one of the AEC coefficients corresponds to a first distance from the audio device and a second one of the AEC coefficients corresponds to a second distance from the audio device; and a gesture detection element configured to:
receive, from the acoustic echo cancellation element, the sequence of AEC coefficients;detect a first proximity of an object to the audio device based at least in part on relative positions of the AEC coefficients within the sequence and amplitudes of a least a portion of the AEC coefficients in the sequence within a first set of the sequence of AEC coefficients corresponding to a first time;detect a second proximity of the object to the audio device based at least in part on relative positions of the AEC coefficients within the sequence and amplitudes of the least a portion of the AEC coefficients in the sequence within a second set of the sequence of AEC coefficients corresponding to a second time; anddeclare a gesture event when the first proximity of the object to the audio device and the second proximity of the object to the audio device indicate that the object is near the audio device and moving toward the audio device.