Cough detection

1. A method of cough detection in a headset, the method comprising:

receiving a first signal from an external transducer of the headset;

receiving a second signal from an in-ear transducer of the headset; and

detecting a cough of a user of the headset based on the first and second signals.

2. The method of claim 1 , wherein detecting the cough comprises:

detecting a cough event in the first signal;

detecting a cough event in the second signal.

3. The method of claim 2 , wherein detecting the cough comprises:

determining a correlation between the cough event in the first audio signal and a cough event in the second signal.

4. The method of claim 1 , wherein detecting the cough comprises:

determining a first energy in a first frequency band of the first signal;

determining a second energy in a second frequency band of the first signal; and

determining an third energy in a third frequency band of the second signal, wherein the first frequency band having a higher centre frequency than the second frequency band and the third frequency band.

5. The method of claim 4 , wherein:

determining the first energy comprises high pass filtering the first signal;

determining the second energy comprises low pass filtering the first signal; and

determining the third energy comprises low pass filtering the second signal.

6. The method of claim 1 , further comprising:

determining a change of orientation of the headset; and

detecting the cough based on the change in orientation.

7. The method of claim 6 , wherein the in-ear transducer comprises an accelerometer, and wherein the change of orientation of the headset is determined based on the second signal from the accelerometer.

8. The method of claim 6 , further comprising:

receiving an accelerometer signal from an accelerometer of the headset, wherein the cough is detected based on the first and second signals and the accelerometer signal.

9. The method of claim 8 , wherein the change in orientation is determined based on the accelerometer signal.

10. The method of claim 6 , further comprising:

high-pass filtering the second signal, wherein the cough is detected based on the high-pass filtered second signal.

11. The method of claim 6 , further comprising:

determining a severity of the cough based on the second signal.

12. The method of claim 1 , further comprising:

on detection of the cough, determining one or more characteristics of the cough based on the first and second signals.

13. The method of claim 12 , further comprising:

receiving an accelerometer signal from an accelerometer of the headset; and

determining the one or more characteristics of the cough based on the accelerometer signal.

14. The method of claim 12 , wherein determining the one or more characteristics of the cough comprises:

providing the first and second signals to a neural network.

15. The method of claim 12 , further comprising:

determining a medical condition of the user based on the determined one or more characteristics of the cough.

16. The method of claim 15 , wherein the medical condition comprises asthma or croup or chronic obstructive pulmonary disease (COPD) or pneumonia or coronavirus or influenza.

17. The method of claim 1 , wherein the second transducer is a speaker of the headset.

18. The method of claim 17 , wherein the second signal is generated based on a bias current of the speaker.

19. A non-transitory storage medium having instructions thereon which, when executed by a processor, cause the processor to perform a method comprising:

receiving a first signal from an external transducer of the headset;

receiving a second signal from an in-ear transducer of the headset; and

detecting a cough of a user of the headset based on the first and second signals.

20. An apparatus for cough detection, comprising:

a first input for receiving a first signal from an external transducer of a headset;

a second input for receiving a second signal from an in-ear transducer of the headset; and

one or more processors configured to:

detect a cough of a user of the headset based on the first and second signals.