Systems and methods of reducing acoustic noise
View Patent ↗A wearable device for detecting a user state is disclosed. The wearable device includes one or more of an accelerometer for measuring an acceleration of a user, a magnetometer for measuring a magnetic field associated with the user's change of orientation, and a gyroscope. The wearable device also includes one or more microphones for receiving audio. The wearable device may determine whether the orientation of the wearable device has changed and may designate or re-designate microphones as primary or secondary microphones.
1. A computer-implemented method, comprising:
obtaining, from at least one of a magnetometer, an accelerometer, and a gyroscope, first orientation data associated with a wearable device;
determining, based on the first orientation data, which of a first microphone of the wearable device and a second microphone of the wearable device is closest to a target sound source,
designating the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the target sound source;
designating the other of the first microphone and the second microphone as a secondary microphone for detecting background noise;
identifying, based on the first orientation data, a suspected user state of a user of the wearable device; and
upon receiving audio inputs from the first microphone and the second microphone, categorizing the suspected user state as one of a plurality of user states based on audio inputs received from at least the primary microphone, the plurality of user states comprising a physical state, an emotional state, an activity of daily life, or an inconclusive event.
2. The method of claim 1 , further comprising:
obtaining, from at least one of the accelerometer and the gyroscope, second orientation data associated with the wearable device; and
based on the second orientation data:
determining which of the first microphone and the second microphone is closest to the target sound source; and
re-designating the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the target sound source; and
re-designating the other of the first microphone and the second microphone as a secondary microphone for detecting background noise.
3. The method of claim 2 , wherein the first microphone and the second microphone are re-designated if the second orientation data exceeds a threshold.
4. The method of claim 1 further comprising:
obtaining noise data from the secondary microphone; and
removing noise from audio inputs obtained by the primary microphone using the noise data obtained from the secondary microphone.
5. The method of claim 2 , wherein a time period between obtaining the first orientation data and obtaining the second orientation data is based on an activity of a user.
6. The method of claim 1 , wherein designating the one of the first microphone and the second microphone determined to be closest to the target sound source as the primary microphone and designating the other of the first microphone and the second microphone as the secondary microphone is further based on at least one of an activity of a user or an instruction from a server device configured to analyze the first orientation data.
7. The method of claim 4 , wherein removing noise from audio inputs obtained by the primary microphone using the noise data obtained from the secondary microphone comprises subtracting audio inputs received from the secondary microphone from audio inputs received from the primary microphone.
8. The method of claim 1 , wherein the audio inputs received from the secondary microphone are subtracted from the audio inputs received from the primary microphone before categorizing the suspected user state as one of the plurality of actual user states based on the audio inputs from at least the primary microphone.
9. The method of claim 1 , further comprising determining a first orientation of the wearable device based on the first orientation data.
10. A device, comprising:
a first microphone;
a second microphone;
at least one sensor comprising at least one of a magnetometer, an accelerometer, and a gyroscope; and
a processing device configured to:
obtain, from the at least one sensor, first orientation data associated with the device;
determine, based on the first orientation data, which of the first microphone and the second microphone is closest to a target sound source;
designate, based on the orientation data, the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the sound source; and
designate, based on the orientation data, the other of the first microphone and the second microphone as a secondary microphone for detecting background noise; receive audio inputs from the first microphone and the second microphone;
identify, based on the first orientation data, a suspected user state of a user of the wearable device; and
categorize the suspected user state as one of a plurality of user states based on audio inputs received from at least the primary microphone, the plurality of user states comprising a physical state, an emotional state, an activity of daily life, or an inconclusive event.
11. The device of claim 10 , wherein the processing device is further configured to:
obtain, from at least one of the accelerometer and the gyroscope, second orientation data associated with the device; and
based on the second orientation data:
determine which of the first microphone and the second microphone is closest to the target sound source;
re-designate the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the target sound source; and
re-designate the other of the first microphone and the second microphone as a secondary microphone for detecting background noise.
12. The device of claim 11 , wherein the first microphone and the second microphone are re-designated if the second orientation data exceeds a threshold.
13. The device of claim 10 , wherein the processing device is further configured to:
obtain noise data from the secondary microphone; and
remove noise from audio inputs obtained by the primary microphone using the noise data obtained from the secondary microphone.
14. The device of claim 11 , wherein a time period between obtaining the first orientation data and obtaining the second orientation data is based on an activity of a user.
15. The device of claim 10 , wherein designating the one of the first microphone and the second microphone determined to be closest to the target sound source as the primary microphone and designating the other of the first microphone and the second microphone as the secondary microphone is further based on an activity of a user.
16. The device of claim 10 , wherein designating the one of the first microphone and the second microphone determined to be closest to the target sound source as the primary microphone and designating the other of the first microphone and the second microphone as the secondary microphone is further based on an instruction from a server device configured to analyze the orientation data.
17. A non-transitory computer readable storage medium including instructions that, when executed by a processing system, cause the processing system to perform a method comprising:
obtaining, from at least one of a magnetometer, an accelerometer, and a gyroscope, first orientation data associated with a wearable device;
determining, based on the first orientation data, which of the first microphone and the second microphone is closest to a target sound source;
designating the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the target sound source; and
designating the other of the first microphone and the second microphone as a secondary microphone for detecting background noise;
identifying, based on the first orientation data, a suspected user state of a user of the wearable device; and
upon receiving audio inputs from the first microphone and the second microphone, categorizing the suspected user state as one of a plurality of user states based on audio inputs received from at least the primary microphone, the plurality of user states comprising a physical state, an emotional state, an activity of daily life, or an inconclusive event.
18. The non-transitory computer readable storage medium of claim 17 , wherein the method further comprises:
obtaining, from at least one of the accelerometer and the gyroscope, second orientation data associated with the wearable device; and
based on the second orientation data:
determining which of the first microphone and the second microphone is closest to the target sound source; and
re-designating the one of the first microphone and the second microphone determined to be closest to the target sound source as a primary microphone for detecting sound from the target sound source; and
re-designating the other of the first microphone and the second microphone as a secondary microphone for detecting background noise.
19. The non-transitory computer readable storage medium of claim 18 , wherein the first microphone and the second microphone are re-designated if the additional second orientation data exceeds a threshold.
20. The non-transitory computer readable storage medium of claim 17 , wherein the method further comprises:
obtaining noise data from the secondary microphone; and
removing noise from audio inputs obtained by the primary microphone using the noise data obtained from the secondary microphone.
21. The non-transitory computer readable storage medium of claim 18 ,
wherein a time period between obtaining the first orientation data and obtaining the second orientation data is based on an activity of a user.
22. The non-transitory computer readable storage medium of claim 17 , wherein designating the one of the first microphone and the second microphone determined to be closest to the target sound source as the primary microphone and designating the other of the first microphone and the second microphone as the secondary microphone is further based on an activity of a user.
23. The method of claim 1 , further comprising:
transmitting one or more of the received audio inputs or the first orientation data to a distributed computing system, wherein the distributed computing system is to confirm the categorization of the suspected user state of the user of the wearable device.