Earbud speech estimation
Embodiments of the invention determine a speech estimate using a bone conduction sensor or accelerometer, without employing voice activity detection gating of speech estimation. Speech estimation is based either exclusively on the bone conduction signal, or is performed in combination with a microphone signal. The speech estimate is then used to condition an output signal of the microphone. There are multiple use cases for speech processing in audio devices.
1. A signal processing device for earbud speech estimation, the device comprising:
at least one input for receiving a microphone signal from a microphone of an earbud;
at least one input for receiving a bone conduction sensor signal from a bone conduction sensor of an earbud;
a processor configured to determine from the bone conduction sensor signal at least one characteristic of speech of a user of the earbud, the at least one characteristic being a non-binary variable, the processor further configured to derive from the at least one characteristic of speech at least one signal conditioning parameter; and the processor further configured to use the at least one signal conditioning parameter to condition the microphone signal;
wherein the non-binary variable characteristic of speech determined by the processor from the bone conduction sensor signal is a signal to noise ratio of the bone conduction sensor signal.
2. The signal processing device according to claim 1 , wherein the earbud is a wireless earbud.
3. The signal processing device according to claim 1 , wherein the non-binary variable characteristic of speech determined by the processor from the bone conduction sensor signal is a speech estimate derived from the bone conduction sensor signal.
4. The signal processing device according to claim 3 wherein the processor is configured such that the conditioning of the microphone signal comprises non-stationary noise reduction controlled by the speech estimate derived from the bone conduction sensor signal.
5. The signal processing device according to claim 4 wherein non-stationary noise reduction is further controlled by a speech estimate derived from the microphone signal.
6. The signal processing device according to claim 1 wherein the processor is configured such that the non-binary variable characteristic of speech determined from the bone conduction sensor signal is a speech level of the bone conduction sensor signal.
7. The signal processing device according to claim 1 wherein the processor is configured such that the non-binary variable characteristic of speech determined from the bone conduction sensor signal is an observed spectrum of the bone conduction sensor signal.
8. The signal processing device according to claim 7 wherein the processor is configured such that the non-binary variable characteristic of speech determined from the bone conduction sensor signal is a parametric representation of the spectral envelope of the bone conduction sensor signal.
9. The signal processing device according to claim 1 wherein the processor is configured such that the conditioning of the output signal from the microphone occurs irrespective of voice activity.
10. The signal processing device according to claim 1 wherein the processor is configured such that the at least one signal conditioning parameter comprises band-specific gains derived from the bone conduction sensor signal, and wherein the conditioning of the microphone signal comprises applying the band-specific gains to the microphone signal.
11. The signal processing device according to claim 1 wherein the processor is configured such that the conditioning of the microphone signal comprises applying a Kalman filter process in which the bone conduction sensor signal acts a priori to a speech estimation process.
12. The signal processing device according to claim 1 wherein the processor is configured such that, other than the bone conduction sensor signal being a basis for determination of the at least one characteristic of speech, no component of the bone conduction sensor signal is passed to a signal output of the earbud.
13. The signal processing device according to claim 1 wherein the processor is configured such that, before the non-binary variable characteristic of speech is determined from the bone conduction sensor signal, the bone conduction sensor signal is corrected for observed conditions.
14. The signal processing device according to claim 1 wherein the processor is configured such that the conditioning of the microphone signal is based only upon the non-binary variable characteristic of speech determined from the bone conduction sensor signal.
15. The signal processing device according to claim 1 wherein the bone conduction sensor comprises an accelerometer, which in use is coupled to a surface of the user's ear canal or concha, to detect bone conducted signals from the user's speech.
16. The signal processing device according to claim 1 wherein the bone conduction sensor comprises an in-ear microphone which in use is positioned to detect acoustic sounds arising within the ear canal as a result of bone conduction of the user's speech.
17. The signal processing device according to claim 1 wherein the processor is configured to apply at least one matched filter to the bone conduction sensor signal, the matched filter being configured to match the user's speech in the bone conduction sensor signal to the user's speech in the microphone signal.
18. A method of conditioning an earbud microphone signal, the method comprising:
receiving a bone conduction sensor signal from a bone conduction sensor of an earbud;
receiving a microphone signal from a microphone of the earbud;
determining from the bone conduction sensor signal at least one characteristic of speech of a user of the earbud, the at least one characteristic being a non-binary variable;
deriving from the at least one characteristic of speech at least one signal conditioning parameter; and
using the at least one signal conditioning parameter to condition the output signal from the microphone;
wherein the non-binary variable characteristic of speech determined from the bone conduction sensor signal is a signal to noise ratio of the bone conduction sensor signal.
19. A non-transitory computer readable medium for conditioning an earbud microphone signal, comprising instructions which, when executed by one or more processors, causes performance of the following:
receiving a bone conduction sensor signal from a bone conduction sensor of an earbud;
receiving a microphone signal from a microphone of the earbud;
determining from the bone conduction sensor signal at least one characteristic of speech of a user of the earbud, the at least one characteristic being a non-binary variable;
deriving from the at least one characteristic of speech at least one signal conditioning parameter; and
using the at least one signal conditioning parameter to condition the output signal from the microphone;
wherein the non-binary variable characteristic of speech determined by the processor from the bone conduction sensor signal is a signal to noise ratio of the bone conduction sensor signal.