Apple Inc.
User voice detection based on acoustic near field

Abstract:

Processing sound received by a device can include receiving a first signal from a first microphone of the device and a second signal from a second microphone of the device, where the first and second microphones capture sounds from a sound field. A ratio between the acoustic pressure and the particle velocity of the sound field can be calculated. In response to the ratio exceeding a threshold, speech signal processing is performed on one or more of the microphone signals. Other aspects are also described and claimed.