Biometric processes

1. A method in a biometric authentication system, the biometric authentication system for authenticating a user based on a comparison of audio signals to a stored voice model for an authorised user, the stored voice model being used for speaker recognition of the authorised user, the method comprising:

obtaining a first audio signal that comprises a representation of a bone-conducted signal, wherein the bone-conducted signal is conducted via at least part of the user's skeleton;

obtaining a second audio signal that comprises a representation of an air-conducted signal;

responsive to a determination that the first audio signal comprises a voice signal, enabling updates to the stored voice model for the authorised user based on the second audio signal; and

further to the enablement of updates to the stored voice model for the authorised user, and responsive to authentication of the user as the authorised user, using the second audio signal to update the stored voice model for the authorised user.

2. The method of claim 1 , wherein the user is authenticated as the authorised user based on a biometric process.

3. The method of claim 2 , wherein the biometric process comprises a voice biometric process based on the second audio signal.

4. The method of claim 1 , wherein the user is authenticated as the authorised user based on a non-biometric process.

5. The method of claim 4 , wherein the non-biometric process comprises entry of a password for the authorised user.

6. The method of claim 1 , wherein the step of enabling updates to the stored voice model for the authorised user is further responsive to a determination that the second audio signal comprises a voice signal.

7. The method of claim 1 , wherein the step of enabling updates to the stored voice model for the authorised user based on the second audio signal is further based on a comparison between the first and second audio signals.

8. The method of claim 7 , wherein the step of enabling updates to the stored voice model for the authorised user based on the second audio signal is responsive to detection of a correlation between the first and second audio signals.

9. The method of claim 8 , wherein the step of enabling updates to the stored voice model for the authorised user based on the second audio signal is responsive to detection of a correlation between a part of the first audio signal identified as comprising the voice signal, and a corresponding part of the second audio signal.

10. The method of claim 1 , wherein the first audio signal is generated by an in-ear transducer.

11. The method of claim 1 , wherein the second audio signal is generated by a microphone which is external to the user's ears.

12. A biometric authentication system for authenticating a user based on a comparison of audio signals to a stored voice model for an authorised user, the stored voice model being used for speaker recognition of the authorised user, the biometric authentication system comprising:

a first input for obtaining a first audio signal, the first audio signal comprising a representation of a bone-conducted signal, wherein the bone-conducted signal is conducted via at least part of the user's skeleton;

a second input for obtaining a second audio signal, the second audio signal comprising a representation of an air-conducted signal;

an enablement module operable to determine whether the first audio signal comprises a voice signal and to enable updates to the stored voice model for the authorised user based on the second audio signal, responsive to a determination that the first audio signal comprises a voice signal; and

further comprising a biometric module operable to update the stored voice model for the authorised user using the second audio signal responsive to authentication of the user as the authorised user.

13. The biometric authentication system of claim 12 , further comprising an authentication module operable to authenticate the user as the authorised user based on a biometric process.

14. The biometric authentication system of claim 13 , wherein the biometric process comprises a voice biometric process based on the second audio signal.

15. The biometric authentication system of claim 12 , further comprising an authentication module operable to authenticate the user as the authorised user based on a non-biometric process.

16. The biometric authentication system of claim 15 , wherein the non-biometric process comprises entry of a password for the authorised user.

17. The biometric authentication system of claim 12 , wherein the enablement module is further operable to enable updates to the stored voice model for the authorised user based on the second audio signal responsive to a determination that the air-conducted signal comprises a voice signal.

18. The biometric authentication system of claim 12 , wherein the enablement module is further operable to enable updates to the stored voice model for the authorised user based on the second audio signal based on a comparison of the first and second audio signals.

19. The biometric authentication system of claim 18 , wherein the enablement module is further operable to enable updates to the stored voice model for the authorised user based on the second audio signal responsive to a detection of a correlation between the first and second audio signals.

20. The biometric authentication system of claim 12 , wherein the first input is connectable to a transducer adapted for insertion into a user's ear.

21. The biometric authentication system of claim 12 , wherein the second input is connectable to a voice microphone.

22. The biometric authentication system of claim 12 , wherein the biometric authentication system is provided on a single integrated circuit.

23. An electronic apparatus, for authenticating a user based on a comparison of audio signals to a stored voice model for an authorised user, the stored voice model being used for speaker recognition of the authorised user, the electronic apparatus comprising processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the electronic apparatus to:

obtain a first audio signal that comprises a representation of a bone-conducted signal, wherein the bone-conducted signal is conducted via at least part of the user's skeleton;

obtain a second audio signal that comprises a representation of an air-conducted signal;

responsive to a determination that the first audio signal comprises a voice signal, enable updates to the stored voice model for the authorised user based on the second audio signal; and

update the stored voice model for the authorised user using the second audio signal responsive to authentication of the user as the authorised user.

24. The electronic apparatus according to claim 23 , wherein the electronic apparatus comprises a personal audio device, or a host electronic device.

25. A non-transitory machine-readable medium for authenticating a user based on a comparison of audio signals to a stored voice model for an authorised user, the stored voice model being used for speaker recognition of the authorised user, the medium storing instructions which, when executed by processing circuitry, cause an electronic apparatus to:

obtain a first audio signal that comprises a representation of a bone-conducted signal, wherein the bone-conducted signal is conducted via at least part of the user's skeleton;

obtain a second audio signal that comprises a representation of an air-conducted signal;

responsive to a determination that the first audio signal comprises a voice signal, enable updates to the stored voice model for the authorised user based on the second audio signal; and

update the stored voice model for the authorised user using the second audio signal responsive to authentication of the user as the authorised user.