Voice onset detection
In some embodiments, a first audio signal is received via a first microphone, and a first probability of voice activity is determined based on the first audio signal. A second audio signal is received via a second microphone, and a second probability of voice activity is determined based on the first and second audio signals. Whether a first threshold of voice activity is met is determined based on the first and second probabilities of voice activity. In accordance with a determination that a first threshold of voice activity is met, it is determined that a voice onset has occurred, and an alert is transmitted to a processor based on the determination that the voice onset has occurred. In accordance with a determination that a first threshold of voice activity is not met, it is not determined that a voice onset has occurred.
1. A method comprising:
receiving, via a first microphone, a first audio signal;
determining a first probability of voice activity based on the first audio signal;
receiving, via a second microphone, a second audio signal;
combining the first audio signal and the second audio signal to produce a third audio signal, the third audio signal comprising a beamforming signal;
determining a second probability of voice activity based on the third audio signal;
determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;
in accordance with a determination that the first threshold of voice activity is met:
determining that a voice onset has occurred; and
transmitting an alert to a processor based on the determination that the voice onset has occurred; and
in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred.
2. The method of claim 1 , wherein determining whether the first threshold of voice activity is met comprises:
determining a baseline noise power; and
determining a ratio of the first audio signal to the baseline noise power.
3. The method of claim 1 , wherein determining the second probability of voice activity based on the first audio signal and the second audio signal comprises:
summing the first audio signal and the second audio signal to produce a summation signal;
subtracting the first audio signal and the second audio signal to produce a difference signal; and
calculating a ratio of the difference signal to the summation signal.
4. The method of claim 1 , wherein the first microphone and the second microphone are configured to be equidistant from a user's mouth.
5. The method of claim 1 , wherein the first microphone is configured to be a first distance from a user's mouth, and wherein the second microphone is configured to be a second distance different from the first distance from a user's mouth.
6. The method of claim 5 , the method further comprising determining a time offset associated with a difference between the first distance and the second distance, wherein determining the second probability of voice activity based on the third audio signal further comprises compensating for the time offset.
7. The method of claim 6 , the method further comprising:
applying a window function to the first audio signal;
applying a bandpass filter to the first audio signal;
applying a finite-impulse response (FIR) filter to the second audio signal, the FIR filter associated with the time offset compensation;
applying a window function to the second audio signal; and
applying a bandpass filter to the second audio signal.
8. The method of claim 1 , wherein determining whether the first threshold of voice activity is met comprises:
weighting the first probability of voice activity with a first weight; and
weighting the second probability of voice activity with a second weight.
9. The method of claim 1 , the method further comprising:
in accordance with a determination that the first threshold of voice activity is met, initiating a subsequent processing step.
10. The method of claim 9 , wherein the subsequent processing step comprises determining a content of speech.
11. The method of claim 1 , wherein the first microphone and the second microphone are located on a wearable head device.
12. The method of claim 1 , wherein the determination of whether the first threshold of voice activity is met is based on sensor data from a wearable head device.
13. The method of claim 12 , wherein the sensor data comprises mouth movement data associated with a user of the wearable head device.
14. The method of claim 12 , wherein the sensor data comprises eye movement data associated with a user of the wearable head device.
15. The method of claim 12 , wherein the sensor data comprises vital sign data associated with a user of the wearable head device.
16. A system comprising:
a first microphone;
a second microphone; and
one or more processors configured to perform:
receiving, via the first microphone, a first audio signal;
determining a first probability of voice activity based on the first audio signal;
receiving, via the second microphone, a second audio signal;
combining the first audio signal and the second audio signal to produce a third audio signal, the third audio signal comprising a beamforming signal;
determining a second probability of voice activity based on the third audio signal;
determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;
in accordance with a determination that the first threshold of voice activity is met:
determining that a voice onset has occurred; and
transmitting an alert to a processor of the one or more processors based on the determination that the voice onset has occurred; and
in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred.
17. The system of claim 16 , wherein the first microphone is configured to be a first distance from a user's mouth, and wherein the second microphone is configured to be a second distance different from the first distance from a user's mouth.
18. A non-transitory computer-readable medium storing one or more instructions, which, when executed by one or more processors of an electronic device, cause the device to perform a method comprising:
receiving, via a first microphone, a first audio signal;
determining a first probability of voice activity based on the first audio signal;
receiving, via a second microphone, a second audio signal;
combining the first audio signal and the second audio signal to produce a third audio signal, the third audio signal comprising a beamforming signal;
determining a second probability of voice activity based on the third audio signal;
determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;
in accordance with a determination that the first threshold of voice activity is met:
determining that a voice onset has occurred; and
transmitting an alert to a processor of the one or more processors based on the determination that the voice onset has occurred; and
in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred.
19. The non-transitory computer-readable medium of claim 18 , wherein the first microphone is configured to be a first distance from a user's mouth, and wherein the second microphone is configured to be a second distance different from the first distance from a user's mouth.
20. The non-transitory computer-readable medium of claim 19 , wherein the method further comprises determining a time offset associated with a difference between the first distance and the second distance, wherein determining the second probability of voice activity based on the third audio signal further comprises compensating for the time offset.