Biometric detection using multiple sensors
Aspects of the present disclosure provide methods and apparatuses for estimating a biometric parameter using multiple sensors. As described herein, multiple sensors are strategically used to output with increased confidence a biometric parameter. Multiple sensors are strategically used to save power while determining an accurate biometric estimation. Additionally, multiple sensors are used to detect and categorize a sleep apnea event.
1 . A method for determining a biometric parameter associated with a subject, the method comprising:
receiving a first signal obtained using a first sensor, the first sensor comprising a microphone disposed on an earpiece of an audio device, wherein the first sensor is used to estimate the biometric parameter within a degree of confidence;
determining a signal-to-noise ratio (SNR) of first signal is less than a threshold value for determining the biometric parameter;
signaling a second sensor to receive a second signal upon determining the SNR is less than the threshold, the second sensor being disposed on the audio device, wherein the second sensor is used to estimate the biometric parameter when the first sensor is unable to estimate the biometric parameter within the degree of confidence;
determining the biometric parameter based, at least in part, on the second signal; and
estimating when the subject falls asleep using the biometric parameter.
2 . The method of claim 1 , wherein the second sensor is in a low-power state and in response to the signaling, the second sensor enters a higher-power state.
3 . The method of claim 1 , wherein the audio device comprises a wearable audio device.
4 . The method of claim 1 , wherein the second sensor comprises a photoplethysmogram (PPG) sensor.
5 . The method of claim 1 , wherein the first sensor consumes less power to obtain the first signal than the second sensor consumes to obtain the second signal.
6 . The method of claim 1 , wherein the biometric parameter comprises one of heart beats or respiration rate (RR) of the subject.
7 . The method of claim 6 , further comprising:
determining, based on the biometric parameter, the subject has an anxious mind; and
adjusting an output of the audio device to entrain breathing of the subject based on the determined anxious mind.
8 . The method of claim 1 , further comprising using the biometric parameter and the estimate of the subject falling asleep to create a closed-loop experience, wherein the closed-loop experience comprises adjusting an audio output of the audio device to entrain the subject's breathing to a desired rate.
9 . A system comprising:
an audio device;
a first sensor comprising a microphone disposed on an earpiece of the audio device;
a second sensor; and
a processor coupled to the audio device, the processor being configured to:
receive a first signal obtained using the first sensor, wherein the first sensor is used to estimate the biometric parameter within a degree of confidence;
determine a signal-to-noise ratio (SNR) of first signal is less than a threshold value for determining a biometric parameter associated with a subject;
signal the second sensor to receive a second signal upon determining the SNR is less than the threshold, the second sensor being disposed on the audio device, wherein the second sensor is used to estimate the biometric parameter when the first sensor is unable to estimate the biometric parameter within the degree of confidence;
determine the biometric parameter based, at least in part, on the second signal; and
estimating when the subject falls asleep using the biometric parameter.
10 . The system of claim 9 , wherein the second sensor is in a low-power state and in response to the signal to receive the second signal, the second sensor enters a higher-power state.
11 . The system of claim 9 , wherein the audio device comprises a wearable audio device.
12 . The system of claim 9 , wherein the second sensor comprises a photoplethysmogram (PPG) sensor.
13 . The system of claim 9 , wherein the first sensor consumes less power to obtain the first signal than the second sensor consumes to obtain the second signal.
14 . The system of claim 9 , wherein the biometric parameter comprises one of heart beats or respiration rate (RR) of the subject.
15 . The audio device of claim 14 , wherein the processor is further configured to:
determine, based on the biometric parameter, the subject has an anxious mind; and
adjust an output of the audio device to entrain breathing of the subject based on the determined anxious mind.
16 . A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by a processor of an audio device, cause the audio device to perform a method for determining a biometric parameter associated with a subject, the method comprising:
receiving a first signal obtained using a first sensor, the first sensor comprising a microphone disposed on an earpiece of the audio device, wherein the first sensor is used to estimate the biometric parameter within a degree of confidence;
determining a signal-to-noise ratio (SNR) of first signal is less than a threshold value for determining the biometric parameter;
signaling a second sensor to receive a second signal upon determining the SNR is less than the threshold, the second sensor being disposed on the audio device, wherein the second sensor is used to estimate the biometric parameter when the first sensor is unable to estimate the biometric parameter within the degree of confidence;
determining the biometric parameter based, at least in part, on the second signal, wherein at least one of the first sensor or the second sensor are disposed on the audio device; and
estimating when the subject falls asleep using the biometric parameter.
17 . The non-transitory computer-readable medium of claim 16 , wherein the second sensor is in a low-power state and in response to the signaling, the second sensor enters a higher-power state.
18 . The non-transitory computer-readable medium of claim 16 , wherein the audio device comprises a wearable audio device.
19 . The non-transitory computer-readable medium of claim 16 , wherein the second sensor comprises a photoplethysmogram (PPG) sensor.
20 . The non-transitory computer-readable medium of claim 16 , wherein the biometric parameter comprises one of heart beats or respiration rate (RR) of the subject.
21 . The non-transitory computer-readable medium of claim 20 , wherein the method further comprises:
determining, based on the biometric parameter, the subject has an anxious mind; and
adjusting an output of the audio device to entrain breathing of the subject based on the determined anxious mind.
22 . The method of claim 1 , wherein the first sensor is disposed on an ear-tip of the earpiece of the audio device.
23 . The audio device of claim 9 , wherein the first sensor is disposed on an ear-tip of the earpiece of the audio device.
24 . The non-transitory computer-readable medium of claim 16 , wherein the first sensor is disposed on an ear-tip of the earpiece of the audio device.
25 . The method of claim 1 , wherein signaling the second sensor to receive the second signal preserves a battery of the audio device to enable the battery to last through a period of time that the subject is asleep.
26 . The method of claim 25 , further comprising detecting sleep apnea events while the subject is asleep.